Search Results for author:
Found 105 papers, 58 papers with code
Knowledge-Augmented Methods for Natural Language Processing
Knowledge in natural language processing (NLP) has been a rising trend especially after the advent of large scale pre-trained models.
Knowledge-Enriched Natural Language Generation
Knowledge-enriched text generation poses unique challenges in modeling and learning, driving active research in several core directions, ranging from integrated modeling of neural representations and symbolic information in the sequential/hierarchical/graphical structures, learning without direct supervisions due to the cost of structured annotation, efficient optimization and inference with massive and global constraints, to language grounding on multiple modalities, and generative reasoning with implicit commonsense knowledge and background knowledge.
CLIPErase: Efficient Unlearning of Visual-Textual Associations in CLIP
Machine unlearning (MU) has gained significant attention as a means to remove specific data from trained models without requiring a full retraining process.
Protecting Privacy in Multimodal Large Language Models with MLLMU-Bench
Generative models such as Large Language Models (LLM) and Multimodal Large Language models (MLLMs) trained on massive web corpora can memorize and disclose individuals' confidential and private data, raising legal and ethical concerns.
Shopping MMLU: A Massive Multi-Task Online Shopping Benchmark for Large Language Models
Shopping MMLU consists of 57 tasks covering 4 major shopping skills: concept understanding, knowledge reasoning, user behavior alignment, and multi-linguality, and can thus comprehensively evaluate the abilities of LLMs as general shop assistants.
MultiChartQA: Benchmarking Vision-Language Models on Multi-Chart Problems
Multimodal Large Language Models (MLLMs) have demonstrated impressive abilities across various tasks, including visual question answering and chart comprehension, yet existing benchmarks for chart-related tasks fall short in capturing the complexity of real-world multi-chart scenarios.
Enhancing Mathematical Reasoning in LLMs by Stepwise Correction
Best-of-N decoding methods instruct large language models (LLMs) to generate multiple solutions, score each using a scoring function, and select the highest scored as the final answer to mathematical reasoning problems.
MentalGLM Series: Explainable Large Language Models for Mental Health Analysis on Chinese Social Media
The proposed models were evaluated on three downstream tasks and achieved better or comparable performance compared to deep learning models, generalized LLMs, and task fine-tuned LLMs.
TOWER: Tree Organized Weighting for Evaluating Complex Instructions
Evaluating the ability of large language models (LLMs) to follow complex human-written instructions is essential for their deployment in real-world applications.
Multimodal Large Language Models for Inverse Molecular Design with Retrosynthetic Planning
While large language models (LLMs) have integrated images, adapting them to graphs remains challenging, limiting their applications in materials and drug design.
Leopard: A Vision Language Model For Text-Rich Multi-Image Tasks
Tasks involving multiple text-rich images are especially challenging, as they require not only understanding the content of individual images but reasoning about inter-relationships and logical flows across multiple visual inputs.
CodeTaxo: Enhancing Taxonomy Expansion with Limited Examples via Code Language Prompts
Taxonomies play a crucial role in various applications by providing a structural representation of knowledge.
Machine Unlearning in Generative AI: A Survey
We offer a comprehensive survey on many things about MU in Generative AI, such as a new problem formulation, evaluation methods, and a structured discussion on the advantages and limitations of different kinds of MU techniques.
A Generic Review of Integrating Artificial Intelligence in Cognitive Behavioral Therapy
Cognitive Behavioral Therapy (CBT) is a well-established intervention for mitigating psychological issues by modifying maladaptive cognitive and behavioral patterns.
Distance Recomputator and Topology Reconstructor for Graph Neural Networks
These methods address the limitations of static node representations and fixed aggregation schemes in traditional GNNs, offering a more nuanced approach to modeling complex and dynamic graph topologies.
GraphSnapShot: Graph Machine Learning Acceleration with Fast Storage and Retrieval
In our recent research, we have developed a framework called GraphSnapShot, which has been proven an useful tool for graph learning acceleration.
Learn Beyond The Answer: Training Language Models with Reflection for Mathematical Reasoning
Supervised fine-tuning enhances the problem-solving abilities of language models across various mathematical reasoning tasks.
Learning Molecular Representation in a Cell
A sufficiency objective decodes the representation to align with different feature spaces from the molecule's neighborhood in the context graph.
Personalized Pieces: Efficient Personalized Large Language Models through Collaborative Efforts
Personalized large language models (LLMs) aim to tailor interactions, content, and recommendations to individual user preferences.
Empirical Guidelines for Deploying LLMs onto Resource-constrained Edge Devices
For example, an optimal choice between parameter learning and RAG may vary depending on the difficulty of the downstream task, the longer fine-tuning time does not necessarily help the model, and a compressed LLM may be a better choice than an uncompressed LLM to learn from limited personalized data.
Large Language Models Can Self-Correct with Key Condition Verification
The condition can be an entity in an open-domain question or a numeric value in a math question, which requires minimal effort (via prompting) to identify.
Describe-then-Reason: Improving Multimodal Mathematical Reasoning through Visual Comprehension Training
Open-source multimodal large language models (MLLMs) excel in various tasks involving textual and visual inputs but still struggle with complex multimodal mathematical reasoning, lagging behind proprietary models like GPT-4V(ision) and Gemini-Pro.
AI-Enhanced Cognitive Behavioral Therapy: Deep Learning and Large Language Models for Extracting Cognitive Pathways from Social Media Texts
Cognitive Behavioral Therapy (CBT) is an effective technique for addressing the irrational thoughts stemming from mental illnesses, but it necessitates precise identification of cognitive pathways to be successfully implemented in patient care.
Instructing Large Language Models to Identify and Ignore Irrelevant Conditions
Lastly it instructs the LLMs with the verification on relevant and irrelevant conditions to avoid confusion and improve reasoning paths.
Reference-based Metrics Disprove Themselves in Question Generation
These criteria are not constrained to the syntactic or semantic of a single reference question, and the metric does not require a diverse set of references.
Item-side Fairness of Large Language Model-based Recommendation System
Towards this goal, we develop a concise and effective framework called IFairLRS to enhance the item-side fairness of an LRS.
OpenFMNav: Towards Open-Set Zero-Shot Object Navigation via Vision-Language Foundation Models
By leveraging the reasoning and generalizing abilities of foundation models, our method can understand free-form human instructions and perform effective open-set zero-shot navigation in diverse environments.
Towards Safer Large Language Models through Machine Unlearning
To address this gap, we introduce Selective Knowledge negation Unlearning (SKU), a novel unlearning framework for LLMs, designed to eliminate harmful knowledge while preserving utility on normal prompts.
Chain-of-Layer: Iteratively Prompting Large Language Models for Taxonomy Induction from Limited Examples
Automatic taxonomy induction is crucial for web search, recommendation systems, and question answering.
Democratizing Large Language Models via Personalized Parameter-Efficient Fine-tuning
OPPU integrates parametric user knowledge in the personal PEFT parameters with non-parametric knowledge from retrieval and profiles, adapting LLMs to user behavior shifts.
TrustLLM: Trustworthiness in Large Language Models
This paper introduces TrustLLM, a comprehensive study of trustworthiness in LLMs, including principles for different dimensions of trustworthiness, established benchmark, evaluation, and analysis of trustworthiness for mainstream LLMs, and discussion of open challenges and future directions.
Get an A in Math: Progressive Rectification Prompting
Given an initial answer from CoT, PRP iterates a verify-then-rectify process to progressively identify incorrect answers and rectify the reasoning paths.
User Modeling in the Era of Large Language Models: Current Research and Future Directions
Two common types of user data are text and graph, as the data usually contain a large amount of user-generated content (UGC) and online interactions.
Large Language Models on Graphs: A Comprehensive Survey
Besides, although LLMs have shown their pure text-based reasoning ability, it is underexplored whether such ability can be generalized to graphs (i. e., graph-based reasoning).
Enabling On-Device Large Language Model Personalization with Self-Supervised Data Selection and Synthesis
While it is possible to obtain annotation locally by directly asking users to provide preferred responses, such annotations have to be sparse to not affect user experience.
PLUG: Leveraging Pivot Language in Cross-Lingual Instruction Tuning
Instruction tuning has remarkably advanced large language models (LLMs) in understanding and responding to diverse human instructions.
Explaining Tree Model Decisions in Natural Language for Network Intrusion Detection
Finally, we show LLM generated decision tree explanations correlate highly with human ratings of readability, quality, and use of background knowledge while simultaneously providing better understanding of decision boundaries.
Auto-Instruct: Automatic Instruction Generation and Ranking for Black-Box Language Models
Large language models (LLMs) can perform a wide range of tasks by following natural language instructions, without the necessity of task-specific fine-tuning.
Current and future directions in network biology
Network biology is an interdisciplinary field bridging computational and biological sciences that has proved pivotal in advancing the understanding of cellular functions and diseases across biological systems and scales.
Embedding Mental Health Discourse for Community Recommendation
Our paper investigates the use of discourse embedding techniques to develop a community recommendation system that focuses on mental health support groups on social media.
Investigating Cross-Domain Behaviors of BERT in Review Understanding
Review score prediction requires review text understanding, a critical real-world application of natural language processing.
A Quantitative Review on Language Model Efficiency Research
Language models (LMs) are being scaled and becoming powerful.
Improving Language Models via Plug-and-Play Retrieval Feedback
ReFeed first generates initial outputs, then utilizes a retrieval model to acquire relevant information from large document collections, and finally incorporates the retrieved information into the in-context demonstration for output refinement, thereby addressing the limitations of LLMs in a more efficient and cost-effective manner.
IfQA: A Dataset for Open-domain Question Answering under Counterfactual Presuppositions
Although counterfactual reasoning is a fundamental aspect of intelligence, the lack of large-scale counterfactual open-domain question-answering (QA) benchmarks makes it difficult to evaluate and improve models on this ability.
Pre-training Language Models for Comparative Reasoning
Comparative reasoning is a process of comparing objects, concepts, or entities to draw conclusions, which constitutes a fundamental cognitive ability.
Exploring Contrast Consistency of Open-Domain Question Answering Systems on Minimally Edited Questions
Contrast consistency, the ability of a model to make consistently correct predictions in the presence of perturbations, is an essential aspect in NLP.
Semi-Supervised Graph Imbalanced Regression
The training data balance is achieved by (1) pseudo-labeling more graphs for under-represented labels with a novel regression confidence measurement and (2) augmenting graph examples in latent space for remaining rare labels after data balancing with pseudo-labels.
Large Language Models are Built-in Autoregressive Search Engines
To overcome this limitation, recent autoregressive search engines replace the dual-encoder architecture by directly generating identifiers for relevant documents in the candidate pool.
Data-Centric Learning from Unlabeled Graphs with Diffusion Model
A conventional approach is training a model with the unlabeled graphs on self-supervised tasks and then fine-tuning the model on the prediction tasks.
Very Large Language Model as a Unified Methodology of Text Mining
Text data mining is the process of deriving essential information from language text.
Retrieval Augmentation for Commonsense Reasoning: A Unified Approach
However, applying such methods to commonsense reasoning tasks faces two unique challenges, i. e., the lack of a general large-scale corpus for retrieval and a corresponding effective commonsense retriever.
A Unified Encoder-Decoder Framework with Entity Memory
The entity knowledge is stored in the memory as latent representations, and the memory is pre-trained on Wikipedia along with encoder-decoder parameters.
Generate rather than Retrieve: Large Language Models are Strong Context Generators
We call our method generate-then-read (GenRead), which first prompts a large language model to generate contextutal documents based on a given question, and then reads the generated documents to produce the final answer.
Heterogeneous Line Graph Transformer for Math Word Problems
We originally planned to employ existing models but realized that they processed a math word problem as a sequence or a homogeneous graph of tokens.
On the Relationship Between Counterfactual Explainer and Recommender
To enable explainability, recent techniques such as ACCENT and FIA are looking for counterfactual explanations that are specific historical actions of a user, the removal of which leads to a change to the recommendation result.
Automatic Controllable Product Copywriting for E-Commerce
Automatic product description generation for e-commerce has witnessed significant advancement in the past decade.
Graph Rationalization with Environment-based Augmentations
Rationale is defined as a subset of input features that best explains or supports the prediction by machine learning models.
Ranked #1 on
Graph Regression
on GlassTemp
A Bottom-Up End-User Intelligent Assistant Approach to Empower Gig Workers against AI Inequality
The AI inequality is caused by (1) the technology divide in who has access to AI technologies in gig work; and (2) the data divide in who owns the data in gig work leads to unfair working conditions, growing pay gap, neglect of workers' diverse preferences, and workers' lack of trust in the platforms.
A Survey of Multi-task Learning in Natural Language Processing: Regarding Task Relatedness and Training Methods
Multi-task learning (MTL) has become increasingly popular in natural language processing (NLP) because it improves the performance of related tasks by exploiting their commonalities and differences.
Diversifying Content Generation for Commonsense Reasoning with Mixture of Knowledge Graph Experts
A set of knowledge experts seek diverse reasoning on KG to encourage various generation outputs.
Graph Data Augmentation for Graph Machine Learning: A Survey
Overall, our work aims to clarify the landscape of existing literature in graph data augmentation and motivates additional work in this area, providing a helpful resource for researchers and practitioners in the broader graph machine learning domain.
Dict-BERT: Enhancing Language Model Pre-training with Dictionary
In addition to training with the masked language modeling objective, we propose two novel self-supervised pre-training tasks on word and sentence-level alignment between input text sequence and rare word definitions to enhance language modeling representation with dictionary.
Multi-Round Parsing-based Multiword Rules for Scientific OpenIE
Information extraction (IE) in scientific literature has facilitated many down-stream tasks.
Enhancing Taxonomy Completion with Concept Generation via Fusing Relational Representations
Automatic construction of a taxonomy supports many applications in e-commerce, web search, and question answering.
Learning from Counterfactual Links for Link Prediction
However, the causal relationship between the two variables was largely ignored for learning to predict links on a graph.
Ranked #1 on
Link Property Prediction
on ogbl-ddi
Cross-Network Learning with Partially Aligned Graph Convolutional Networks
Graph neural networks have been widely used for learning representations of nodes for many downstream tasks on graph data.
Modeling multi-scale data via a network of networks
Prediction of node and graph labels are prominent network science tasks.
Sentence-Permuted Paragraph Generation
Generating paragraphs of diverse contents is important in many applications.
TCN: Table Convolutional Network for Web Table Interpretation
Existing work linearize table cells and heavily rely on modifying deep language models such as BERT which only captures related cells information in the same table.
Few-Shot Graph Learning for Molecular Property Prediction
The recent success of graph neural networks has significantly boosted molecular property prediction, advancing activities such as drug discovery.
Ranked #1 on
Molecular Property Prediction (1-shot))
on Tox21
Traceability Transformed: Generating moreAccurate Links with Pre-Trained BERT Models
In this study, we propose a novel framework called Trace BERT (T-BERT) to generate trace links between source code and natural language artifacts.
Transfer Learning
Software Engineering
Validating Label Consistency in NER Data Annotation
It can be used to validate the label consistency (or catches the inconsistency) in multiple sets of NER data annotation.
FGNAS: FPGA-Aware Graph Neural Architecture Search
The success of gragh neural networks (GNNs) in the past years has aroused grow-ing interest and effort in designing best models to handle graph-structured data.
Tri-Train: Automatic Pre-Fine Tuning between Pre-Training and Fine-Tuning for SciNER
The training process of scientific NER models is commonly performed in two steps: i) Pre-training a language model by self-supervised tasks on huge data and ii) fine-tune training with small labelled data.
Few-Shot Multi-Hop Relation Reasoning over Knowledge Bases
Multi-hop relation reasoning over knowledge base is to generate effective and interpretable relation prediction through reasoning paths.
Action Sequence Augmentation for Early Graph-based Anomaly Detection
With Eland, anomaly detection performance at an earlier stage is better than non-augmented methods that need significantly more observed data by up to 15% on the Area under the ROC curve.
Technical Question Answering across Tasks and Domains
In this paper, we propose a novel framework of deep transfer learning to effectively address technical QA across tasks and domains.
A Technical Question Answering System with Transfer Learning
In recent years, the need for community technical question-answering sites has increased significantly.
Injecting Entity Types into Entity-Guided Text Generation
Our model has a multi-step decoder that injects the entity types into the process of entity mention generation.
Federated Dynamic GNN with Secure Aggregation
Given video data from multiple personal devices or street cameras, can we exploit the structural and dynamic information to learn dynamic representation of objects for applications such as distributed surveillance, without storing data at a central server that leads to a violation of user privacy?
Learning Attribute-Structure Co-Evolutions in Dynamic Graphs
In this work, we present a novel framework called CoEvoGNN for modeling dynamic attributed graph sequence.
Specification mining and automated task planning for autonomous robots based on a graph-based spatial temporal logic
For knowledge representation, we use a graph-based spatial temporal logic (GSTL) to capture spatial and temporal information of related skills demonstrated by demo videos.
Canonicalizing Open Knowledge Bases with Multi-Layered Meta-Graph Neural Network
Noun phrases and relational phrases in Open Knowledge Bases are often not canonical, leading to redundant and ambiguous facts.
Data Augmentation for Graph Neural Networks
Our work shows that neural edge predictors can effectively encode class-homophilic structure to promote intra-class edges and demote inter-class edges in given graph structure, and our main contribution introduces the GAug graph data augmentation framework, which leverages these insights to improve performance in GNN-based node classification via edge prediction.
Ranked #1 on
Node Classification
on Flickr
Calendar Graph Neural Networks for Modeling Time Structures in Spatiotemporal User Behaviors
The user embeddings preserve spatial patterns and temporal patterns of a variety of periodicity (e. g., hourly, weekly, and weekday patterns).
A Probabilistic Model with Commonsense Constraints for Pattern-based Temporal Fact Extraction
Textual patterns (e. g., Country's president Person) are specified and/or generated for extracting factual information from unstructured data.
Crossing Variational Autoencoders for Answer Retrieval
Existing methods learned semantic representations with dual encoders or dual variational auto-encoders.
Enhancing Factual Consistency of Abstractive Summarization
Automatic abstractive summaries are found to often distort or fabricate facts in the article.
Heterogeneous Relational Reasoning in Knowledge Graphs with Reinforcement Learning
Path-based relational reasoning over knowledge graphs has become increasingly popular due to a variety of downstream applications such as question answering in dialogue systems, fact prediction, and recommender systems.
Improving Generalizability of Fake News Detection Methods using Propensity Score Matching
Recently, due to the booming influence of online social networks, detecting fake news is drawing significant attention from both academic communities and general public.
Few-Shot Knowledge Graph Completion
Knowledge graphs (KGs) serve as useful resources for various natural language processing applications.
Faceted Hierarchy: A New Graph Type to Organize Scientific Concepts and a Construction Method
On a scientific concept hierarchy, a parent concept may have a few attributes, each of which has multiple values being a group of child concepts.
Multi-Input Multi-Output Sequence Labeling for Joint Extraction of Fact and Condition Tuples from Scientific Text
In this work, we propose a new sequence labeling framework (as well as a new tag schema) to jointly extract the fact and condition tuples from statement sentences.
Graph Few-shot Learning via Knowledge Transfer
Towards the challenging problem of semi-supervised node classification, there have been extensive studies.
MSU-Net: Multiscale Statistical U-Net for Real-time 3D Cardiac MRI Video Segmentation
Cardiac magnetic resonance imaging (MRI) is an essential tool for MRI-guided surgery and real-time intervention.
Constructing Information-Lossless Biological Knowledge Graphs from Conditional Statements
Conditions are essential in the statements of biological literature.
TaxoGen: Unsupervised Topic Taxonomy Construction by Adaptive Term Embedding and Clustering
Our method, TaxoGen, uses term embeddings and hierarchical clustering to construct a topic taxonomy in a recursive fashion.
Databases
PBGen: Partial Binarization of Deconvolution-Based Generators for Edge Intelligence
This work explores the binarization of the deconvolution-based generator in a GAN for memory saving and speedup of image construction.
MetaPAD: Meta Pattern Discovery from Massive Text Corpora
We propose an efficient framework, called MetaPAD, which discovers meta patterns from massive corpora with three techniques: (1) it develops a context-aware segmentation method to carefully determine the boundaries of patterns with a learnt pattern quality assessment function, which avoids costly dependency parsing and generates high-quality patterns; (2) it identifies and groups synonymous meta patterns from multiple facets---their types, contexts, and extractions; and (3) it examines type distributions of entities in the instances extracted by each group of patterns, and looks for appropriate type levels to make discovered patterns precise.
Automated Phrase Mining from Massive Text Corpora
As one of the fundamental tasks in text analysis, phrase mining aims at extracting quality phrases from a text corpus.
DPPred: An Effective Prediction Framework with Concise Discriminative Patterns
In the literature, two series of models have been proposed to address prediction problems including classification and regression.
