Search Results for author:
Found 312 papers, 88 papers with code
Uncertain Local-to-Global Networks for Document-Level Event Factuality Identification
Moreover, we propose an Uncertain Information Aggregation module to leverage the global structure for integrating the local information.
Document-Level Relation Extraction via Pair-Aware and Entity-Enhanced Representation Learning
Document-level relation extraction aims to recognize relations among multiple entity pairs from a whole piece of article.
CogKGE: A Knowledge Graph Embedding Toolkit and Benchmark for Representing Multi-source and Heterogeneous Knowledge
Designing CogKGE aims to provide a unified programming framework for KGE tasks and a series of knowledge representations for downstream tasks.
Enhancing Multiple-choice Machine Reading Comprehension by Punishing Illogical Interpretations
Multiple-choice MRC is one of the most studied tasks in MRC due to the convenience of evaluation and the flexibility of answer format.
Biomedical Concept Normalization by Leveraging Hypernyms
Biomedical Concept Normalization (BCN) is widely used in biomedical text processing as a fundamental module.
Domain-Lifelong Learning for Dialogue State Tracking via Knowledge Preservation Networks
This paradigm is often impractical in real-world applications since online dialogue systems usually involve continually emerging new data and domains.
Read Extensively, Focus Smartly: A Cross-document Semantic Enhancement Method for Visual Documents NER
To deal with this problem, this work proposes a cross-document semantic enhancement method, which consists of two modules: 1) To prevent distractions from irrelevant regions in the current document, we design a learnable attention mask mechanism, which is used to adaptively filter redundant information in the current document.
Generating Temporally-ordered Event Sequences via Event Optimal Transport
The other issue is that the model adopts a word-level objective to model events in texts, failing to evaluate the predicted results of the model from the perspective of event sequence.
Augmentation, Retrieval, Generation: Event Sequence Prediction with a Three-Stage Sequence-to-Sequence Approach
Currently existing approach models this task as a statistical induction problem, to predict a sequence of events by exploring the similarity between the given goal and the known sequences of events.
CMQA: A Dataset of Conditional Question Answering with Multiple-Span Answers
To bridge the gap, we propose a new task: conditional question answering with hierarchical multi-span answers, where both the hierarchical relations and the conditions need to be extracted.
Decoupling Mixture-of-Graphs: Unseen Relational Learning for Knowledge Graph Completion by Fusing Ontology and Textual Experts
In fact, the semantics of a relation can be expressed by three kinds of graphs: factual graph, ontology graph, textual description graph, and they can complement each other.
CASIA at SemEval-2022 Task 11: Chinese Named Entity Recognition for Complex and Ambiguous Entities
This paper describes our approach to develop a complex named entity recognition system in SemEval 2022 Task 11: MultiCoNER Multilingual Complex Named Entity Recognition, Track 9 - Chinese.
LingJing at SemEval-2022 Task 3: Applying DeBERTa to Lexical-level Presupposed Relation Taxonomy with Knowledge Transfer
For the classification sub-task, we adopt the DeBERTa-v3 pre-trained model for fine-tuning datasets of different languages.
Chinese Named Entity Recognition via Adaptive Multi-pass Memory Network with Hierarchical Tagging Mechanism
Specifically, to reduce the errors of predicting entity boundaries, we propose an adaptive multi-pass memory network to exploit lexical knowledge.
Chinese Named Entity Recognition
named-entity-recognition
+3
FedED: Federated Learning via Ensemble Distillation for Medical Relation Extraction
In this paper, we propose a privacy-preserving medical relation extraction model based on federated learning, which enables training a central model with no single piece of private local data being shared or exchanged.
Incremental Event Detection via Knowledge Consolidation Networks
However, existing incremental learning methods cannot handle semantic ambiguity and training data imbalance problems between old and new classes in the task of incremental event detection.
CroAno : A Crowd Annotation Platform for Improving Label Consistency of Chinese NER Dataset
2) Inconsistency Detector: CroAno employs a detector to locate corpus-level label inconsistency and provides users an interface to correct inconsistent entities in batches.
Set Generation Networks for End-to-End Knowledge Base Population
In this paper, we formulate end-to-end KBP as a direct set generation problem, avoiding considering the order of multiple facts.
Classification, Extraction, and Normalization : CASIA_Unisound Team at the Social Media Mining for Health 2021 Shared Tasks
This is the system description of the CASIA_Unisound team for Task 1, Task 7b, and Task 8 of the sixth Social Media Mining for Health Applications (SMM4H) shared task in 2021.
Scene Restoring for Narrative Machine Reading Comprehension
Inspired by this behavior of humans, we propose a method to let the machine imagine a scene during reading narrative for better comprehension.
Knowledge Transfer with Visual Prompt in multi-modal Dialogue Understanding and Generation
In this work, we propose a knowledge transfer method with visual prompt (VPTG) fusing multi-modal data, which is a flexible module that can utilize the text-only seq2seq model to handle visual dialogue tasks.
CASIA@SMM4H’22: A Uniform Health Information Mining System for Multilingual Social Media Texts
This paper presents a description of our system in SMM4H-2022, where we participated in task 1a, task 4, and task 6 to task 10.
Leveraging Explicit Lexico-logical Alignments in Text-to-SQL Parsing
Text-to-SQL aims to parse natural language questions into SQL queries, which is valuable in providing an easy interface to access large databases.
Incremental Intent Detection for Medical Domain with Contrast Replay Networks
We first formulate incremental learning for medical intent detection.
Evaluating Personalized Tool-Augmented LLMs from the Perspectives of Personalization and Proactivity
Personalized tool utilization is essential for aligning large language models (LLMs) with user preference in interaction scenarios with various tools.
GATE: Graph-based Adaptive Tool Evolution Across Diverse Tasks
Large Language Models (LLMs) have shown great promise in tool-making, yet existing frameworks often struggle to efficiently construct reliable toolsets and are limited to single-task settings.
The Knowledge Microscope: Features as Better Analytical Lenses than Neurons
Previous studies primarily utilize MLP neurons as units of analysis for understanding the mechanisms of factual knowledge in Language Models (LMs); however, neurons suffer from polysemanticity, leading to limited knowledge expression and poor interpretability.
Does RAG Really Perform Bad For Long-Context Processing?
The efficient processing of long context poses a serious challenge for large language models (LLMs).
DATA: Decomposed Attention-based Task Adaptation for Rehearsal-Free Continual Learning
For new tasks, DATA dynamically adjusts the weights of adapters of different ranks based on their relevance and distinction from previous tasks, allowing the model to acquire new task-specific skills while effectively retaining previously learned knowledge.
SAMRefiner: Taming Segment Anything Model for Universal Mask Refinement
In contrast to prior refinement techniques that are tailored to specific models or tasks in a close-world manner, we propose SAMRefiner, a universal and efficient approach by adapting SAM to the mask refinement task.
VaiBot: Shuttle Between the Instructions and Parameters
Through experiments, we demonstrate that VaiBot performs on par with existing baseline methods in terms of deductive capabilities while significantly surpassing them in inductive capabilities.
RAG-RewardBench: Benchmarking Reward Models in Retrieval Augmented Generation for Preference Alignment
Despite the significant progress made by existing retrieval augmented language models (RALMs) in providing trustworthy responses and grounding in reliable sources, they often overlook effective alignment with human preferences.
A Survey on Private Transformer Inference
Transformer models have revolutionized AI, enabling applications like content generation and sentiment analysis.
Towards Adaptive Mechanism Activation in Language Agent
Language Agent could be endowed with different mechanisms for autonomous task accomplishment.
One Mind, Many Tongues: A Deep Dive into Language-Agnostic Knowledge Neurons in Large Language Models
Some researchers attempt to demystify the factual knowledge in LLMs from the perspective of knowledge neurons, and subsequently discover language-agnostic knowledge neurons that store factual knowledge in a form that transcends language barriers.
Data Processing Efficiency Aware User Association and Resource Allocation in Blockchain Enabled Metaverse over Wireless Communications
It uniquely alternates the optimization of key variables like user association, work offloading ratios, task-specific computing resource distribution, bandwidth allocation, user power usage ratios, and server computing resource allocation ratios.
LLaSA: Large Language and Structured Data Assistant
Specifically, we represent various types of structured data in a unified hypergraph format, and use self-supervised learning to pretrain a hypergraph encoder, and a G-Former compressing encoded hypergraph representations with cross-attention.
JoyVASA: Portrait and Animal Image Animation with Diffusion-Based Audio-Driven Facial Dynamics and Head Motion Generation
Specifically, in the first stage, we introduce a decoupled facial representation framework that separates dynamic facial expressions from static 3D facial representations.
DTELS: Towards Dynamic Granularity of Timeline Summarization
The rapid proliferation of online news has posed significant challenges in tracking the continuous development of news topics.
Commonsense Knowledge Editing Based on Free-Text in LLMs
Knowledge editing technology is crucial for maintaining the accuracy and timeliness of large language models (LLMs) .
PGDiffSeg: Prior-Guided Denoising Diffusion Model with Parameter-Shared Attention for Breast Cancer Segmentation
Therefore, this paper proposes a novel PGDiffSeg (Prior-Guided Diffusion Denoising Model with Parameter-Shared Attention) that applies diffusion denoising methods to breast cancer medical image segmentation, accurately recovering the affected areas from Gaussian noise.
A Troublemaker with Contagious Jailbreak Makes Chaos in Honest Towns
With the development of large language models, they are widely used as agents in various fields.
MIRAGE: Evaluating and Explaining Inductive Reasoning Process in Language Models
Inductive reasoning is an essential capability for large language models (LLMs) to achieve higher intelligence, which requires the model to generalize rules from observed facts and then apply them to unseen examples.
LINKED: Eliciting, Filtering and Integrating Knowledge in Large Language Model for Commonsense Reasoning
In it, we design a reward model to filter out the noisy knowledge and take the marginal consistent reasoning module to reduce invalid reasoning.
DA-Code: Agent Data Science Code Generation Benchmark for Large Language Models
We introduce DA-Code, a code generation benchmark specifically designed to assess LLMs on agent-based data science tasks.
Efficient Length-Generalizable Attention via Causal Retrieval for Long-Context Language Modeling
In this paper, we propose a novel attention mechanism based on dynamic context, Grouped Cross Attention (GCA), which can generalize to 1000 times the pre-training context length while maintaining the ability to access distant information with a constant attention window size.
Resource Allocation for Stable LLM Training in Mobile Edge Computing
As mobile devices increasingly become focal points for advanced applications, edge computing presents a viable solution to their inherent computational limitations, particularly in deploying large language models (LLMs).
JoyType: A Robust Design for Multilingual Visual Text Creation
In this paper, we introduce a novel approach for multilingual visual text creation, named JoyType, designed to maintain the font style of text during the image generation process.
JoyHallo: Digital human model for Mandarin
In audio-driven video generation, creating Mandarin videos presents significant challenges.
CITI: Enhancing Tool Utilizing Ability in Large Language Models without Sacrificing General Performance
However, previous works predominantly focus on improving model's tool-utilizing accuracy and the ability to generalize to new, unseen tools, excessively forcing LLMs to adjust specific tool-invoking pattern without considering the harm to model's general performance.
Neural-Symbolic Collaborative Distillation: Advancing Small Language Models for Complex Reasoning Tasks
By decoupling general and specialized capabilities, the proposed NesyCD can achieve superior performance cost-effectively, utilizing smaller models and blending parameterized neural networks with symbolic KB.
$\textit{SKIntern}$: Internalizing Symbolic Knowledge for Distilling Better CoT Capabilities into Small Language Models
By efficiently internalizing knowledge, $\textit{SKIntern}$ reduces computational overhead and speeds up the reasoning process by focusing solely on the question during inference.
MHAD: Multimodal Home Activity Dataset with Multi-Angle Videos and Synchronized Physiological Signals
This non-contact, real-time monitoring method holds great potential for home settings.
Does Knowledge Localization Hold True? Surprising Differences Between Entity and Relation Perspectives in Language Models
Contrary to prior research suggesting that knowledge is stored in MLP weights, our experiments demonstrate that relational knowledge is also significantly encoded in attention modules.
Large Language Models as Foundations for Next-Gen Dense Retrieval: A Comprehensive Empirical Assessment
In this work, we conduct a comprehensive empirical study on a wide range of retrieval tasks, including in domain accuracy, data efficiency, zero shot generalization, lengthy retrieval, instruction based retrieval, and multi task learning.
Towards Robust Knowledge Unlearning: An Adversarial Framework for Assessing and Improving Unlearning Robustness in Large Language Models
In response to this vulnerability, we propose Latent Adversarial Unlearning (LAU), a universal framework that effectively enhances the robustness of the unlearned process.
Knowledge in Superposition: Unveiling the Failures of Lifelong Knowledge Editing for Large Language Models
Moreover, this is the first study to investigate knowledge editing from the perspective of superposition and provides a comprehensive observation of superposition across numerous real-world language models.
TransferTOD: A Generalizable Chinese Multi-Domain Task-Oriented Dialogue System with Transfer Capabilities
Task-oriented dialogue (TOD) systems aim to efficiently handle task-oriented conversations, including information collection.
Beyond Instruction Following: Evaluating Inferential Rule Following of Large Language Models
The experimental results show that through IRFT, LLMs can learn abstract rule-following abilities from purely synthetic data and then generalize to RuleBench.
Multilingual Knowledge Graph Completion from Pretrained Language Models with Knowledge Constraints
Multilingual Knowledge Graph Completion (mKGC) aim at solving queries like (h, r, ?)
Find Parent then Label Children: A Two-stage Taxonomy Completion Method with Pre-trained Language Model
Taxonomies, which organize domain concepts into hierarchical structures, are crucial for building knowledge systems and downstream applications.
CogMG: Collaborative Augmentation Between Large Language Model and Knowledge Graph
In this work, we introduce a collaborative augmentation framework, CogMG, leveraging knowledge graphs to address the limitations of LLMs in QA scenarios, explicitly targeting the problems of incomplete knowledge coverage and knowledge update misalignment.
Unlocking the Future: Exploring Look-Ahead Planning Mechanistic Interpretability in Large Language Models
In this work, we focus on exploring the look-ahead planning mechanism in large language models from the perspectives of information flow and internal representations.
Improving Zero-shot LLM Re-Ranker with Risk Minimization
In the Retrieval-Augmented Generation (RAG) system, advanced Large Language Models (LLMs) have emerged as effective Query Likelihood Models (QLMs) in an unsupervised way, which re-rank documents based on the probability of generating the query given the content of a document.
Beyond Under-Alignment: Atomic Preference Enhanced Factuality Tuning for Large Language Models
Extensive experiments demonstrate that APEFT improves model performance by an average of $\boldsymbol{3. 45\%}$ on both ID and OOD datasets, which is highly effective.
From Instance Training to Instruction Learning: Task Adapters Generation from Instructions
Within this context, we introduce Task Adapters Generation from Instructions (TAGI), which automatically constructs the task-specific model in a parameter generation manner based on the given task instructions without retraining for unseen tasks.
MEMLA: Enhancing Multilingual Knowledge Editing with Neuron-Masked Low-Rank Adaptation
In this paper, we focus on multilingual knowledge editing (MKE), which requires propagating updates across multiple languages.
RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language Models
Large language models (LLMs) inevitably memorize sensitive, copyrighted, and harmful knowledge from the training corpus; therefore, it is crucial to erase this knowledge from the models.
Towards Faithful Chain-of-Thought: Large Language Models are Bridging Reasoners
Large language models (LLMs) suffer from serious unfaithful chain-of-thought (CoT) issues.
Verifying Properties of Binary Neural Networks Using Sparse Polynomial Optimization
This paper explores methods for verifying the properties of Binary Neural Networks (BNNs), focusing on robustness against adversarial attacks.
Knowledge Localization: Mission Not Accomplished? Enter Query Localization!
This theory is based on the knowledge localization (KL) assumption, which suggests that a fact can be localized to a few knowledge storage units, namely knowledge neurons.
Generate-on-Graph: Treat LLM as both Agent and KG in Incomplete Knowledge Graph Question Answering
To simulate these real-world scenarios and evaluate the ability of LLMs to integrate internal and external knowledge, we propose leveraging LLMs for QA under Incomplete Knowledge Graph (IKGQA), where the provided KG lacks some of the factual triples for each question, and construct corresponding datasets.
Self-Demos: Eliciting Out-of-Demonstration Generalizability in Large Language Models
The generated demos strategically interpolate between existing demos and the given query, transforming the query from OOD to ID.
STBA: Towards Evaluating the Robustness of DNNs for Query-Limited Black-box Scenario
Many attack techniques have been proposed to explore the vulnerability of DNNs and further help to improve their robustness.
Continual Few-shot Event Detection via Hierarchical Augmentation Networks
The CFED task is challenging as it involves memorizing previous event types and learning new event types with few-shot samples.
RSTAR4D: Rotational Streak Artifact Reduction in 4D CBCT using a Separable 4D CNN
We find that streak artifacts exhibit a unique rotational motion along with the patient's respiration, distinguishable from diaphragm-driven respiratory motion in the spatiotemporal domain.
Awakening Augmented Generation: Learning to Awaken Internal Knowledge of Large Language Models for Question Answering
Retrieval-Augmented-Generation and Generation-Augmented-Generation have been proposed to enhance the knowledge required for question answering with Large Language Models (LLMs) by leveraging richer context.
Open-Domain Question Answering
Out-of-Distribution Generalization
Perennial Semantic Data Terms of Use for Decentralized Web
We believe this work demonstrates a practicality of a perennial DToU language and the potential of a paradigm shift to how users interact with data and applications in a decentralized Web, offering both improved privacy and usability.
ItD: Large Language Models Can Teach Themselves Induction through Deduction
Although Large Language Models (LLMs) are showing impressive performance on a wide range of Natural Language Processing tasks, researchers have found that they still have limited ability to conduct induction.
From Chain to Tree: Refining Chain-like Rules into Tree-like Rules on Knowledge Graphs
With good explanatory power and controllability, rule-based methods play an important role in many tasks such as knowledge reasoning and decision support.
Zero-Shot Cross-Lingual Document-Level Event Causality Identification with Heterogeneous Graph Contrastive Transfer Learning
Event Causality Identification (ECI) refers to the detection of causal relations between events in texts.
AgentsCourt: Building Judicial Decision-Making Agents with Court Debate Simulation and Legal Knowledge Augmentation
With the development of deep learning, natural language processing technology has effectively improved the efficiency of various aspects of the traditional judicial industry.
Whispers that Shake Foundations: Analyzing and Mitigating False Premise Hallucinations in Large Language Models
Large Language Models (LLMs) have shown impressive capabilities but still suffer from the issue of hallucinations.
Focus on Your Question! Interpreting and Mitigating Toxic CoT Problems in Commonsense Reasoning
Large language models exhibit high-level commonsense reasoning abilities, especially with enhancement methods like Chain-of-Thought (CoT).
Cutting Off the Head Ends the Conflict: A Mechanism for Interpreting and Mitigating Knowledge Conflicts in Language Models
Moreover, we reveal that the pivotal point at which knowledge conflicts emerge in LMs is the integration of inconsistent information flows by memory heads and context heads.
Tug-of-War Between Knowledge: Exploring and Resolving Knowledge Conflicts in Retrieval-Augmented Language Models
Then, we investigate the behavior and preference of RALMs from the following two perspectives: (1) Conflicts between internal memory and external sources: We find that stronger RALMs emerge with the Dunning-Kruger effect, persistently favoring their faulty internal memory even when correct evidence is provided.
Unveiling Linguistic Regions in Large Language Models
Furthermore, this core region exhibits significant dimensional dependence, perturbations to even a single parameter on specific dimensions leading to a loss of linguistic competence.
Cracking Factual Knowledge: A Comprehensive Analysis of Degenerate Knowledge Neurons in Large Language Models
Large language models (LLMs) store extensive factual knowledge, but the underlying mechanisms remain unclear.
MoELoRA: Contrastive Learning Guided Mixture of Experts on Parameter-Efficient Fine-Tuning for Large Language Models
Fine-tuning is often necessary to enhance the adaptability of Large Language Models (LLM) to downstream tasks.
Discerning and Resolving Knowledge Conflicts through Adaptive Decoding with Contextual Information-Entropy Constraint
Large language models internalize enormous parametric knowledge during pre-training.
LongAgent: Scaling Language Models to 128k Context through Multi-Agent Collaboration
Large language models (LLMs) have demonstrated impressive performance in understanding language and executing complex reasoning tasks.
Advancing Translation Preference Modeling with RLHF: A Step Towards Cost-Effective Solution
To address this issue, we propose a cost-effective preference learning strategy, optimizing reward models by distinguishing between human and machine translations.
LongHeads: Multi-Head Attention is Secretly a Long Context Processor
Instead of allowing each head to attend to the full sentence, which struggles with generalizing to longer sequences due to out-of-distribution (OOD) issues, we allow each head to process in-distribution length by selecting and attending to important context chunks.
WilKE: Wise-Layer Knowledge Editor for Lifelong Knowledge Editing
Knowledge editing aims to rectify inaccuracies in large language models (LLMs) without costly retraining for outdated or erroneous knowledge.
ControlLM: Crafting Diverse Personalities for Language Models
This heightens the need to control model behaviors.
Enhancing Large Language Models with Pseudo- and Multisource- Knowledge Graphs for Open-ended Question Answering
In summary, our results pave the way for enhancing LLMs by incorporating Pseudo- and Multisource-KGs, particularly in the context of open-ended questions.
HyCubE: Efficient Knowledge Hypergraph 3D Circular Convolutional Embedding
It is desirable and challenging for knowledge hypergraph embedding to reach a trade-off between model effectiveness and efficiency.
Device Scheduling and Assignment in Hierarchical Federated Learning for Internet of Things
For scalability, practical HFL schemes select a subset of IoT devices to participate in the training, hence the notion of device scheduling.
DE$^3$-BERT: Distance-Enhanced Early Exiting for BERT based on Prototypical Networks
DE$^3$-BERT implements a hybrid exiting strategy that supplements classic entropy-based local information with distance-based global information to enhance the estimation of prediction correctness for more reliable early exiting decisions.
Deep Learning Innovations in Diagnosing Diabetic Retinopathy: The Potential of Transfer Learning and the DiaCNN Model
The InceptionResNetv2 model, incorporating transfer learning, registered an impressive 97. 5% accuracy in both the training and testing phases.
A Survey on the Applications of Frontier AI, Foundation Models, and Large Language Models to Intelligent Transportation Systems
This survey paper explores the transformative influence of frontier AI, foundation models, and Large Language Models (LLMs) in the realm of Intelligent Transportation Systems (ITS), emphasizing their integral role in advancing transportation intelligence, optimizing traffic management, and contributing to the realization of smart cities.
Secrets of RLHF in Large Language Models Part II: Reward Modeling
We introduce a series of novel methods to mitigate the influence of incorrect and ambiguous preferences in the dataset and fully leverage high-quality preference data.
LLaMA Beyond English: An Empirical Study on Language Capability Transfer
In recent times, substantial advancements have been witnessed in large language models (LLMs), exemplified by ChatGPT, showcasing remarkable proficiency across a range of complex tasks.
LoRAMoE: Alleviate World Knowledge Forgetting in Large Language Models via MoE-Style Plugin
Supervised fine-tuning (SFT) is a crucial step for large language models (LLMs), enabling them to align with human instructions and enhance their capabilities in downstream tasks.
SSTA: Salient Spatially Transformed Attack
Extensive studies have demonstrated that deep neural networks (DNNs) are vulnerable to adversarial attacks, which brings a huge security risk to the further application of DNNs, especially for the AI models developed in the real world.
Mobile Edge Computing and AI Enabled Web3 Metaverse over 6G Wireless Communications: A Deep Reinforcement Learning Approach
In spite of the rapid advancements in current technologies, the computation required for a smooth, seamless and immersive socialization experience in the Metaverse is overbearing, and the accumulated user experience is essential to be considered.
Offloading and Quality Control for AI Generated Content Services in 6G Mobile Edge Computing Networks
In pursuit of enhancing the accessibility of AIGC services, the deployment of AIGC models (e. g., diffusion models) to edge servers and local devices has become a prevailing trend.
Resource Allocation for Semantic Communication under Physical-layer Security
The secrecy rate is the communication rate at which no information is disclosed to an eavesdropper.
Oasis: Data Curation and Assessment System for Pretraining of Large Language Models
To this end, we present a pretraining corpus curation and assessment platform called Oasis -- a one-stop system for data quality improvement and quantification with user-friendly interactive interfaces.
ExpNote: Black-box Large Language Models are Better Task Solvers with Experience Notebook
Black-box Large Language Models (LLMs) have shown great power in solving various tasks and are considered general problem solvers.
Revolutionizing Global Food Security: Empowering Resilience through Integrated AI Foundation Models and Data-Driven Solutions
Food security, a global concern, necessitates precise and diverse data-driven solutions to address its multifaceted challenges.
Orchestration of Emulator Assisted Mobile Edge Tuning for AI Foundation Models: A Multi-Agent Deep Reinforcement Learning Approach
The efficient deployment and fine-tuning of foundation models are pivotal in contemporary artificial intelligence.
FedPEAT: Convergence of Federated Learning, Parameter-Efficient Fine Tuning, and Emulator Assisted Tuning for Artificial Intelligence Foundation Models with Mobile Edge Computing
FedPEAT uses adapters, emulators, and PEFT for federated model tuning, enhancing model privacy and memory efficiency.
Unveiling A Core Linguistic Region in Large Language Models
We have discovered a core region in LLMs that corresponds to linguistic competence, accounting for approximately 1% of the total model parameters.
S3Eval: A Synthetic, Scalable, Systematic Evaluation Suite for Large Language Models
The rapid development of Large Language Models (LLMs) has led to great strides in model capabilities like long-context understanding and reasoning.
TableQAKit: A Comprehensive and Practical Toolkit for Table-based Question Answering
Table-based question answering (TableQA) is an important task in natural language processing, which requires comprehending tables and employing various reasoning ways to answer the questions.
Query2Triple: Unified Query Encoding for Answering Diverse Complex Queries over Knowledge Graphs
However, these methods train KG embeddings and neural set operators concurrently on both simple (one-hop) and complex (multi-hop and logical) queries, which causes performance degradation on simple queries and low training efficiency.
Generative Calibration for In-context Learning
In this paper, we for the first time theoretically and empirically identify that such a paradox is mainly due to the label shift of the in-context model to the data distribution, in which LLMs shift the label marginal $p(y)$ while having a good label conditional $p(x|y)$.
SCME: A Self-Contrastive Method for Data-free and Query-Limited Model Extraction Attack
However, the distribution of these fake data lacks diversity and cannot detect the decision boundary of the target model well, resulting in the dissatisfactory simulation effect.
Can LSH (Locality-Sensitive Hashing) Be Replaced by Neural Network?
With the rapid development of GPU (Graphics Processing Unit) technologies and neural networks, we can explore more appropriate data structures and algorithms.
Boosting Black-box Attack to Deep Neural Networks with Conditional Diffusion Models
Existing black-box attacks have demonstrated promising potential in creating adversarial examples (AE) to deceive deep learning models.
Loose lips sink ships: Mitigating Length Bias in Reinforcement Learning from Human Feedback
Reinforcement learning from human feedback serves as a crucial bridge, aligning large language models with human and societal values.
MenatQA: A New Dataset for Testing the Temporal Comprehension and Reasoning Abilities of Large Language Models
As a result, it is natural for people to believe that LLMs have also mastered abilities such as time understanding and reasoning.
HRoT: Hybrid prompt strategy and Retrieval of Thought for Table-Text Hybrid Question Answering
Answering numerical questions over hybrid contents from the given tables and text(TextTableQA) is a challenging task.
User Assignment and Resource Allocation for Hierarchical Federated Learning over Wireless Networks
The large population of wireless users is a key driver of data-crowdsourced Machine Learning (ML).
MMHQA-ICL: Multimodal In-context Learning for Hybrid Question Answering over Text, Tables and Images
Most importantly, we propose a Type-specific In-context Learning Strategy for MMHQA, enabling LLMs to leverage their powerful performance in this task.
Interpreting Sentiment Composition with Latent Semantic Tree
As the key to sentiment analysis, sentiment composition considers the classification of a constituent via classifications of its contained sub-constituents and rules operated on them.
ZhuJiu: A Multi-dimensional, Multi-faceted Chinese Benchmark for Large Language Models
To this end, we propose the ZhuJiu benchmark, which has the following strengths: (1) Multi-dimensional ability coverage: We comprehensively evaluate LLMs across 7 ability dimensions covering 51 tasks.
Journey to the Center of the Knowledge Neurons: Discoveries of Language-Independent Knowledge Neurons and Degenerate Knowledge Neurons
We design cross-lingual knowledge editing experiments, demonstrating that the PLMs can accomplish this task based on language-independent neurons; (2) The discovery of Degenerate Knowledge Neurons, a novel type of neuron showing that different knowledge neurons can store the same fact.
LMTuner: An user-friendly and highly-integrable Training Framework for fine-tuning Large Language Models
With the burgeoning development in the realm of large language models (LLMs), the demand for efficient incremental training tailored to specific industries and domains continues to increase.
SHARK: A Lightweight Model Compression Approach for Large-scale Recommender Systems
Increasing the size of embedding layers has shown to be effective in improving the performance of recommendation models, yet gradually causing their sizes to exceed terabytes in industrial recommender systems, and hence the increase of computing and storage costs.
UAV-assisted Semantic Communication with Hybrid Action Reinforcement Learning
In this paper, we aim to explore the use of uplink semantic communications with the assistance of UAV in order to improve data collection effiicency for metaverse users in remote areas.
Heterogeneous 360 Degree Videos in Metaverse: Differentiated Reinforcement Learning Approaches
Advanced video technologies are driving the development of the futuristic Metaverse, which aims to connect users from anywhere and anytime.
Actively Supervised Clustering for Open Relation Extraction
The key to the setting is selecting which instances to label.
RE-Matching: A Fine-Grained Semantic Matching Method for Zero-Shot Relation Extraction
However, general matching methods lack explicit modeling of the above matching pattern.
Open Set Relation Extraction via Unknown-Aware Training
Inspired by text adversarial attacks, we adaptively apply small but critical perturbations to original training instances and thus synthesizing negative instances that are more likely to be mistaken by the model as known relations.
A Hybrid Framework of Reinforcement Learning and Convex Optimization for UAV-Based Autonomous Metaverse Data Collection
Unmanned aerial vehicles (UAVs) are promising for providing communication services due to their advantages in cost and mobility, especially in the context of the emerging Metaverse and Internet of Things (IoT).
Towards Graph-hop Retrieval and Reasoning in Complex Question Answering over Textual Database
In Textual question answering (TQA) systems, complex questions often require retrieving multiple textual fact chains with multiple reasoning steps.
S$^3$HQA: A Three-Stage Approach for Multi-hop Text-Table Hybrid Question Answering
In this paper, we propose a three-stage TextTableQA framework S3HQA, which comprises of retriever, selector, and reasoner.
Large Language Models Need Holistically Thought in Medical Conversational QA
The medical conversational question answering (CQA) system aims at providing a series of professional medical services to improve the efficiency of medical care.
Multi-View Graph Representation Learning for Answering Hybrid Numerical Reasoning Question
Hybrid question answering (HybridQA) over the financial report contains both textual and tabular data, and requires the model to select the appropriate evidence for the numerical reasoning task.
Mastering Symbolic Operations: Augmenting Language Models with Compiled Neural Networks
Our work highlights the potential of seamlessly unifying explicit rule learning via CoNNs and implicit pattern learning in LMs, paving the way for true symbolic comprehension capabilities.
Towards Adversarially Robust Continual Learning
Recent studies show that models trained by continual learning can achieve the comparable performances as the standard supervised learning and the learning flexibility of continual learning models enables their wide applications in the real world.
Detection of Uncertainty in Exceedance of Threshold (DUET): An Adversarial Patch Localizer
We then conduct further analyses on our choice of model priors and the adoption of Bayesian Neural Networks in different layers within our model architecture.
Mobile Edge Adversarial Detection for Digital Twinning to the Metaverse with Deep Reinforcement Learning
Nevertheless, as real-time, accurate detection of adversarial patches is compute-intensive, these physical world scenes have to be offloaded to the Metaverse Map Base Stations (MMBS) for computation.
Virtual Reality in Metaverse over Wireless Networks with User-centered Deep Reinforcement Learning
Virtual reality (VR) technologies are the backbone for the virtual universe within the Metaverse as they enable a hyper-realistic and immersive experience, and especially so in the context of socialization.
User-centric Heterogeneous-action Deep Reinforcement Learning for Virtual Reality in the Metaverse over Wireless Networks
In this paper, for a system consisting of a Metaverse server and multiple VR users, we consider two cases of (i) the server generating frames and transmitting them to users, and (ii) users generating frames locally and thus consuming device energy.
Knowledge Reasoning via Jointly Modeling Knowledge Graphs and Soft Rules
The former has high accuracy and good interpretability, but a major challenge is to obtain effective rules on large-scale KGs.
UAV aided Metaverse over Wireless Communications: A Reinforcement Learning Approach
A huge amount of data in physical world needs to be synchronized to the virtual world to provide immersive experience for users, and there will be higher requirements on coverage to include more users into Metaverse.
Asynchronous Hybrid Reinforcement Learning for Latency and Reliability Optimization in the Metaverse over Wireless Communications
In the DL stage, the larger-size 3D virtual objects need to be transmitted back to the XUs.
Unified, User and Task (UUT) Centered Artificial Intelligence for Metaverse Edge Computing
The Metaverse can be considered the extension of the present-day web, which integrates the physical and virtual worlds, delivering hyper-realistic user experiences.
Large Language Models are Better Reasoners with Self-Verification
By performing a backward verification of the answers that LLM deduced for itself, we can obtain interpretable answer validation scores to select the candidate answer with the highest score.
Mobile Augmented Reality with Federated Learning in the Metaverse
The Metaverse is deemed the next evolution of the Internet and has received much attention recently.
Resource Allocation of Federated Learning for the Metaverse with Mobile Augmented Reality
The Metaverse has received much attention recently.
Generating Hierarchical Explanations on Text Classification Without Connecting Rules
The opaqueness of deep NLP models has motivated the development of methods for interpreting how deep models predict.
ReasonChainQA: Text-based Complex Question Answering with Explainable Evidence Chains
Recently, natural language database (NLDB) conducts complex QA in knowledge base with textual evidences rather than structured representations, this task attracts a lot of attention because of the flexibility and richness of textual evidence.
Edge-Cloud Cooperation for DNN Inference via Reinforcement Learning and Supervised Learning
A reinforcement learning (RL)-based DNN compression approach is used to generate the lightweight model suitable for the edge from the heavyweight model.
Time Minimization in Hierarchical Federated Learning
Therefore, we formulate a joint learning and communication optimization problem to minimize total model parameter communication and computation delay, by optimizing local iteration counts and edge iteration counts.
Facial Landmark Predictions with Applications to Metaverse
This research aims to make metaverse characters more realistic by adding lip animations learnt from videos in the wild.
Joint Optimization of Energy Consumption and Completion Time in Federated Learning
Federated Learning (FL) is an intriguing distributed machine learning approach due to its privacy-preserving characteristics.
Resource Allocation and Resolution Control in the Metaverse with Mobile Augmented Reality
With the development of blockchain and communication techniques, the Metaverse is considered as a promising next-generation Internet paradigm, which enables the connection between reality and the virtual world.
Mobile Edge Computing, Metaverse, 6G Wireless Communications, Artificial Intelligence, and Blockchain: Survey and Their Convergence
Compared to cloud computing, as the distributed and closer infrastructure, the convergence of MEC with other emerging technologies, including the Metaverse, 6G wireless communications, artificial intelligence (AI), and blockchain, also solves the problems of network resource allocation, more network load as well as latency requirements.
Resource Allocation for Mobile Metaverse with the Internet of Vehicles over 6G Wireless Communications: A Deep Reinforcement Learning Approach
Being able to access scenes and information associated with the physical world, in the Metaverse in real-time and under mobility, is essential in developing a highly accessible, interactive and interconnective experience for all users.
Answering Numerical Reasoning Questions in Table-Text Hybrid Contents with Graph-based Encoder and Tree-based Decoder
In the real-world question answering scenarios, hybrid form combining both tabular and textual contents has attracted more and more attention, among which numerical reasoning problem is one of the most typical and challenging problems.
P2ANet: A Dataset and Benchmark for Dense Action Detection from Table Tennis Match Broadcasting Videos
While deep learning has been widely used for video analytics, such as video classification and action detection, dense action detection with fast-moving subjects from sports videos is still challenging.
LingYi: Medical Conversational Question Answering System based on Multi-modal Knowledge Graphs
The medical conversational system can relieve the burden of doctors and improve the efficiency of healthcare, especially during the pandemic.
Robust PCA Unrolling Network for Super-resolution Vessel Extraction in X-ray Coronary Angiography
Although robust PCA has been increasingly adopted to extract vessels from X-ray coronary angiography (XCA) images, challenging problems such as inefficient vessel-sparsity modelling, noisy and dynamic background artefacts, and high computational cost still remain unsolved.
Towards Efficiently Evaluating the Robustness of Deep Neural Networks in IoT Systems: A GAN-based Method
Through extensive experiments, AI-GAN achieves high attack success rates, outperforming existing methods, and reduces generation time significantly.
Optimizing the Age of Information in RIS-aided SWIPT Networks
In this letter, a reconfigurable intelligent surface (RIS)-assisted simultaneous wireless information and power transfer (SWIPT) network is investigated.
Adversarial Purification through Representation Disentanglement
Deep learning models are vulnerable to adversarial examples and make incomprehensible mistakes, which puts a threat on their real-world deployment.
A Relation-Oriented Clustering Method for Open Relation Extraction
The clustering-based unsupervised relation discovery method has gradually become one of the important methods of open relation extraction (OpenRE).
Ranked #1 on
Relation Extraction
on FewRel
Logic Traps in Evaluating Attribution Scores
Meanwhile, since the reasoning process of deep models is inaccessible, researchers design various evaluation methods to demonstrate their arguments.
Lifelong Intent Detection via Multi-Strategy Rebalancing
In this paper, we propose Lifelong Intent Detection (LID), which continually trains an ID model on new data to learn newly emerging intents while avoiding catastrophically forgetting old data.
Knowledge-Enriched Event Causality Identification via Latent Structure Induction Networks
Specifically, to make use of the descriptive knowledge, we devise a Descriptive Graph Induction module to obtain and encode the graph-structured descriptive knowledge.
A Large-Scale Chinese Multimodal NER Dataset with Speech Clues
In this paper, we aim to explore an uncharted territory, which is Chinese multimodal named entity recognition (NER) with both textual and acoustic contents.
CogIE: An Information Extraction Toolkit for Bridging Texts and CogNet
CogNet is a knowledge base that integrates three types of knowledge: linguistic knowledge, world knowledge and commonsense knowledge.
Document-level Event Extraction via Parallel Prediction Networks
We argue that sentence-level extractors are ill-suited to the DEE task where event arguments always scatter across sentences and multiple events may co-exist in a document.
Automatic ICD Coding via Interactive Shared Representation Networks with Self-distillation Mechanism
The ICD coding task aims at assigning codes of the International Classification of Diseases in clinical notes.
Alignment Rationale for Natural Language Inference
Deep learning models have achieved great success on the task of Natural Language Inference (NLI), though only a few attempts try to explain their behaviors.
Economic Dispatch of an Integrated Microgrid Based on the Dynamic Process of CCGT Plant
Intra-day economic dispatch of an integrated microgrid is a fundamental requirement to integrate distributed generators.
Inconspicuous Adversarial Patches for Fooling Image Recognition Systems on Mobile Devices
The patches are encouraged to be consistent with the background images with adversarial training while preserving strong attack abilities.
MG-DVD: A Real-time Framework for Malware Variant Detection Based on Dynamic Heterogeneous Graph Learning
In this paper, we propose MG-DVD, a novel detection framework based on dynamic heterogeneous graph learning, to detect malware variants in real time.
LearnDA: Learnable Knowledge-Guided Data Augmentation for Event Causality Identification
On the other hand, our approach employs a dual mechanism, which is a learnable augmentation framework and can interactively adjust the generation process to generate task-related sentences.
Improving Event Causality Identification via Self-Supervised Representation Learning on External Causal Statement
Current models for event causality identification (ECI) mainly adopt a supervised framework, which heavily rely on labeled data for training.
Path-based knowledge reasoning with textual semantic information for medical knowledge graph completion
To address the above issues, this paper proposes two novel path-based reasoning methods to solve the sparsity issues of entity and path respectively, which adopts the textual semantic information of entities and paths for MedKGC.
Probing into the Root: A Dataset for Reason Extraction of Structural Events from Financial Documents
This paper proposes a new task regarding event reason extraction from document-level texts.
TextFlint: Unified Multilingual Robustness Evaluation Toolkit for Natural Language Processing
To guarantee user acceptability, all the text transformations are linguistically based, and we provide a human evaluation for each one.
CogNet: Bridging Linguistic Knowledge, World Knowledge and Commonsense Knowledge
In this paper, we present CogNet, a knowledge base (KB) dedicated to integrating three types of knowledge: (1) linguistic knowledge from FrameNet, which schematically describes situations, objects and events.
Joint Transmit Precoding and Reflect Beamforming Design for IRS-Assisted MIMO Cognitive Radio Systems
Cognitive radio (CR) is an effective solution to improve the spectral efficiency (SE) of wireless communications by allowing the secondary users (SUs) to share spectrum with primary users (PUs).
Information Theory Signal Processing Information Theory
Recent Advances in Adversarial Training for Adversarial Robustness
Adversarial training is one of the most effective approaches defending against adversarial examples for deep learning models.
Spectrum Sharing for 6G Integrated Satellite-Terrestrial Communication Networks Based on NOMA and Cognitive Radio
ISTCN aims to provide high speed and pervasive network services by integrating broadband terrestrial mobile networks with satellite communication networks.
Smart City Enabled by 5G/6G Networks: An Intelligent Hybrid Random Access Scheme
mMTC and URLLC will co-exist in MTC networks for 5G 6G-enabled smart city.
Sum-Rate Maximization for UAV-assisted Visible Light Communications using NOMA: Swarm Intelligence meets Machine Learning
As the integration of unmanned aerial vehicles (UAVs) into visible light communications (VLC) can offer many benefits for massive-connectivity applications and services in 5G and beyond, this work considers a UAV-assisted VLC using non-orthogonal multiple-access.
EXPLORING VULNERABILITIES OF BERT-BASED APIS
We then demonstrate how the extracted model can be exploited to develop effective attribute inference attack to expose sensitive information of the training data.
ANL: Anti-Noise Learning for Cross-Domain Person Re-Identification
Usually, attributed to the domain gaps, the pre-trained source domain model cannot extract appropriate target domain features, which will dramatically affect the clustering performance and the accuracy of pseudo-labels.
An LSTM-Aided Hybrid Random Access Scheme for 6G Machine Type Communication Networks
In this paper, an LSTM-aided hybrid random access scheme (LSTMH-RA) is proposed to support diverse quality of service (QoS) requirements in 6G machine-type communication (MTC) networks, where massive MTC (mMTC) devices and ultra-reliable low latency communications (URLLC) devices coexist.
Intelligent Reflecting Surface Assisted Anti-Jamming Communications Based on Reinforcement Learning
Aiming to enhance the communication performance against smart jammer, an optimization problem for jointly optimizing power allocation at the base station (BS) and reflecting beamforming at the IRS is formulated.
A Comprehensive Survey of 6G Wireless Communications
First, we give an overview of 6G from perspectives of technologies, security and privacy, and applications.
