Search Results for author:
Found 89 papers, 55 papers with code
Do Pre-trained Models Benefit Knowledge Graph Completion? A Reliable Evaluation and a Reasonable Approach
In recent years, pre-trained language models (PLMs) have been shown to capture factual knowledge from massive texts, which encourages the proposal of PLM-based knowledge graph completion (KGC) models.
MMEKG: Multi-modal Event Knowledge Graph towards Universal Representation across Modalities
Events are fundamental building blocks of real-world happenings.
DocEE: A Large-Scale and Fine-grained Benchmark for Document-level Event Extraction
Event extraction aims to identify an event and then extract the arguments participating in the event.
Precise Localization of Memories: A Fine-grained Neuron-level Knowledge Editing Technique for LLMs
Knowledge editing aims to update outdated information in Large Language Models (LLMs).
Pairwise RM: Perform Best-of-N Sampling with Knockout Tournament
To address this, we propose a Pairwise Reward Model (Pairwise RM) combined with a knockout tournament for BoN sampling.
Long Context vs. RAG for LLMs: An Evaluation and Revisits
Extending context windows (i. e., Long Context, LC) and using retrievers to selectively access relevant information (i. e., Retrieval-Augmented Generation, RAG) are the two main strategies to enable LLMs to incorporate extremely long external contexts.
Simulation-Free Hierarchical Latent Policy Planning for Proactive Dialogues
It fully automates the process from mining policies in dialogue records to learning policy planning.
Hierarchical Reinforcement Learning
Reinforcement Learning (RL)
+1
EvoWiki: Evaluating LLMs on Evolving Knowledge
Knowledge utilization is a critical aspect of LLMs, and understanding how they adapt to evolving knowledge is essential for their effective deployment.
ForgerySleuth: Empowering Multimodal Large Language Models for Image Manipulation Detection
Moreover, we construct the ForgeryAnalysis dataset through the Chain-of-Clues prompt, which includes analysis and reasoning text to upgrade the image manipulation detection task.
Multi-Programming Language Sandbox for LLMs
We introduce MPLSandbox, an out-of-the-box multi-programming language sandbox designed to provide unified and comprehensive feedback from compiler and analysis tools for Large Language Models (LLMs).
RM-Bench: Benchmarking Reward Models of Language Models with Subtlety and Style
However, this approach fails to assess reward models on subtle but critical content changes and variations in style, resulting in a low correlation with policy model performance.
ChartifyText: Automated Chart Generation from Data-Involved Texts via LLM
It consists of two major modules: tabular data inference and expressive chart generation.
Grounded-VideoLLM: Sharpening Fine-grained Temporal Grounding in Video Large Language Models
Video Large Language Models (Video-LLMs) have demonstrated remarkable capabilities in coarse-grained video understanding, however, they struggle with fine-grained temporal grounding.
Complex Logical Query Answering by Calibrating Knowledge Graph Completion Models
The core concept of CKGC is to map the values of predictions of KGC models to the range [0, 1], ensuring that values associated with true facts are close to 1, while values linked to false facts are close to 0.
Knowledge Graph Embedding by Normalizing Flows
To reflect uncertainty, we first embed entities/relations as permutations of a set of random variables.
Navigating the Nuances: A Fine-grained Evaluation of Vision-Language Navigation
The framework is structured around the context-free grammar (CFG) of the task.
LogicPro: Improving Complex Logical Reasoning via Program-Guided Learning
In this paper, we present a novel approach, called LogicPro, to enhance Large Language Models (LLMs) complex Logical reasoning through Program Examples.
Diagnosing and Remedying Knowledge Deficiencies in LLMs via Label-free Curricular Meaningful Learning
This makes it a challenge to diagnose and remedy the deficiencies of LLMs through rich label-free user queries.
MMLongBench-Doc: Benchmarking Long-context Document Understanding with Visualizations
Moreover, 33. 2% of the questions are cross-page questions requiring evidence across multiple pages.
LLMs-as-Instructors: Learning from Errors Toward Automating Model Improvement
Inspired by the theory of "Learning from Errors", this framework employs an instructor LLM to meticulously analyze the specific errors within a target model, facilitating targeted and efficient training cycles.
LLMs Assist NLP Researchers: Critique Paper (Meta-)Reviewing
This study focuses on the topic of LLMs assist NLP Researchers, particularly examining the effectiveness of LLM in assisting paper (meta-)reviewing and its recognizability.
QRMeM: Unleash the Length Limitation through Question then Reflection Memory Mechanism
While large language models (LLMs) have made notable advancements in natural language processing, they continue to struggle with processing extensive text.
Planning Like Human: A Dual-process Framework for Dialogue Planning
In proactive dialogue, the challenge lies not just in generating responses but in steering conversations toward predetermined goals, a task where Large Language Models (LLMs) typically struggle due to their reactive nature.
A + B: A General Generator-Reader Framework for Optimizing LLMs to Unleash Synergy Potential
In this paper, we formalize a general "A + B" framework with varying combinations of foundation models and types for systematic investigation.
Analyzing Temporal Complex Events with Large Language Models? A Benchmark towards Temporal, Long Context Understanding
We refer to the complex events composed of many news articles over an extended period as Temporal Complex Event (TCE).
Combinatorial Approximations for Cluster Deletion: Simpler, Faster, and Better
Cluster deletion is an NP-hard graph clustering objective with applications in computational biology and social network analysis, where the goal is to delete a minimum number of edges to partition a graph into cliques.
Quantifying and Mitigating Unimodal Biases in Multimodal Large Language Models: A Causal Perspective
Within this framework, we conduct an in-depth causal analysis to assess the causal effect of these biases on MLLM predictions.
Meaningful Learning: Enhancing Abstract Reasoning in Large Language Models via Generic Fact Guidance
The results show that our approach not only boosts the general reasoning performance of LLMs but also makes considerable strides towards their capacity for abstract reasoning, moving beyond simple memorization or imitation to a more nuanced understanding and application of generic facts.
Event-level Knowledge Editing
However, natural knowledge updates in the real world come from the occurrences of new events rather than direct changes in factual triplets.
Automating Dataset Updates Towards Reliable and Timely Evaluation of Large Language Models
There are two updating strategies: 1) mimicking strategy to generate similar samples based on original data, preserving stylistic and contextual essence, and 2) extending strategy that further expands existing samples at varying cognitive levels by adapting Bloom's taxonomy of educational objectives.
SciAgent: Tool-augmented Language Models for Scientific Reasoning
To make this task more practical and solvable for LLMs, we introduce a new task setting named tool-augmented scientific reasoning.
FedMKGC: Privacy-Preserving Federated Multilingual Knowledge Graph Completion
As such, the aggregated language model can leverage complementary knowledge from multilingual KGs without demanding raw user data sharing.
SCTc-TE: A Comprehensive Formulation and Benchmark for Temporal Event Forecasting
Temporal complex event forecasting aims to predict the future events given the observed events from history.
To be or not to be? an exploration of continuously controllable prompt engineering
In response, we introduce ControlPE (Continuously Controllable Prompt Engineering).
X-Eval: Generalizable Multi-aspect Text Evaluation via Augmented Instruction Tuning with Auxiliary Evaluation Aspects
Natural Language Generation (NLG) typically involves evaluating the generated text in various aspects (e. g., consistency and naturalness) to obtain a comprehensive assessment.
Finding and Editing Multi-Modal Neurons in Pre-Trained Transformers
Understanding the internal mechanisms by which multi-modal large language models (LLMs) interpret different modalities and integrate cross-modal representations is becoming increasingly critical for continuous improvements in both academia and industry.
MolCA: Molecular Graph-Language Modeling with Cross-Modal Projector and Uni-Modal Adapter
MolCA enables an LM (e. g., Galactica) to understand both text- and graph-based molecular contents via the cross-modal projector.
Ranked #7 on
Molecule Captioning
on ChEBI-20
A Comprehensive Evaluation of Large Language Models on Legal Judgment Prediction
Large language models (LLMs) have demonstrated great potential for domain-specific applications, such as the law domain.
Improving Large Language Models in Event Relation Logical Prediction
More in detail, we first investigate the deficiencies of LLMs in logical reasoning across different tasks.
Towards Verifiable Generation: A Benchmark for Knowledge-aware Language Model Attribution
Although achieving great success, Large Language Models (LLMs) usually suffer from unreliable hallucinations.
Intuitive or Dependent? Investigating LLMs' Behavior Style to Conflicting Prompts
Drawing on cognitive theory, we target the first scenario of decision-making styles where there is no superiority in the conflict and categorize LLMs' preference into dependent, intuitive, and rational/irrational styles.
FOLLOWUPQG: Towards Information-Seeking Follow-up Question Generation
We introduce the task of real-world information-seeking follow-up question generation (FQG), which aims to generate follow-up questions seeking a more in-depth understanding of an initial question and answer.
Context-aware Event Forecasting via Graph Disentanglement
The task of event forecasting aims to model the relational and temporal patterns based on historical events and makes forecasting to what will happen in the future.
Constructing Holistic Spatio-Temporal Scene Graph for Video Semantic Role Labeling
A scene-event mapping mechanism is first designed to bridge the gap between the underlying scene structure and the high-level event semantic structure, resulting in an overall hierarchical scene-event (termed ICE) graph structure.
Exploring & Exploiting High-Order Graph Structure for Sparse Knowledge Graph Completion
The proposed approach comprises two main components: a GNN-based predictor and a reasoning path distiller.
Robust Prompt Optimization for Large Language Models Against Distribution Shifts
In this light, we propose a new problem of robust prompt optimization for LLMs against distribution shifts, which requires the prompt optimized over the labeled source group can simultaneously generalize to an unlabeled target group.
Examining Inter-Consistency of Large Language Models Collaboration: An In-depth Analysis via Debate
Through extensive experiments on various datasets, LLMs can effectively collaborate to reach a consensus despite noticeable inter-inconsistencies, but imbalances in their abilities can lead to domination by superior LLMs.
Information Screening whilst Exploiting! Multimodal Relation Extraction with Feature Denoising and Multimodal Topic Modeling
First, we represent the fine-grained semantic structures of the input image and text with the visual and textual scene graphs, which are further fused into a unified cross-modal graph (CMG).
Take a Break in the Middle: Investigating Subgoals towards Hierarchical Script Generation
Goal-oriented Script Generation is a new task of generating a list of steps that can fulfill the given goal.
Few-shot Event Detection: An Empirical Study and a Unified View
Few-shot event detection (ED) has been widely studied, while this brings noticeable discrepancies, e. g., various motivations, tasks, and experimental settings, that hinder the understanding of models for future progress. This paper presents a thorough empirical study, a unified view of ED models, and a better unified baseline.
Large Language Model Is Not a Good Few-shot Information Extractor, but a Good Reranker for Hard Samples!
Large Language Models (LLMs) have made remarkable strides in various tasks.
R$^2$F: A General Retrieval, Reading and Fusion Framework for Document-level Natural Language Inference
Document-level natural language inference (DOCNLI) is a new challenging task in natural language processing, aiming at judging the entailment relationship between a pair of hypothesis and premise documents.
TGDM: Target Guided Dynamic Mixup for Cross-Domain Few-Shot Learning
The proposed TGDM framework contains a Mixup-3T network for learning classifiers and a dynamic ratio generation network (DRGN) for learning the optimal mix ratio.
Explainable Sparse Knowledge Graph Completion via High-order Graph Reasoning Network
On the one hand, their performance will dramatically degrade along with the increasing sparsity of KGs.
VEM$^2$L: A Plug-and-play Framework for Fusing Text and Structure Knowledge on Sparse Knowledge Graph Completion
In this paper, we solve the sparse KGC from these two motivations simultaneously and handle their respective drawbacks further, and propose a plug-and-play unified framework VEM$^2$L over sparse KGs.
ERGO: Event Relational Graph Transformer for Document-level Event Causality Identification
In this paper, we propose a novel Event Relational Graph TransfOrmer (ERGO) framework for DECI, which improves existing state-of-the-art (SOTA) methods upon two aspects.
Prompt for Extraction? PAIE: Prompting Argument Interaction for Event Argument Extraction
We have conducted extensive experiments on three benchmarks, including both sentence- and document-level EAE.
Information Extraction in Low-Resource Scenarios: Survey and Perspective
Information Extraction (IE) seeks to derive structured information from unstructured texts, often facing challenges in low-resource scenarios due to data scarcity and unseen classes.
What Makes the Story Forward? Inferring Commonsense Explanations as Prompts for Future Event Generation
To alleviate the knowledge forgetting issue, we design two modules, Im and Gm, for each type of knowledge, which are combined via prompt tuning.
Interactive Contrastive Learning for Self-supervised Entity Alignment
Self-supervised entity alignment (EA) aims to link equivalent entities across different knowledge graphs (KGs) without seed alignments.
Training Free Graph Neural Networks for Graph Matching
We present a framework of Training Free Graph Matching (TFGM) to boost the performance of Graph Neural Networks (GNNs) based graph matching, providing a fast promising solution without training (training-free).
Knowledge Graph Completion as Tensor Decomposition: A Genreal Form and Tensor N-rank Regularization
Based on the general form, we show the principles of model design to satisfy logical rules.
Are Missing Links Predictable? An Inferential Benchmark for Knowledge Graph Completion
We present InferWiki, a Knowledge Graph Completion (KGC) dataset that improves upon existing benchmarks in inferential ability, assumptions, and patterns.
How Knowledge Graph and Attention Help? A Qualitative Analysis into Bag-level Relation Extraction
In this paper, we contribute a dataset and propose a paradigm to quantitatively evaluate the effect of attention and KG on bag-level relation extraction (RE).
How Knowledge Graph and Attention Help? A Quantitative Analysis into Bag-level Relation Extraction
In this paper, we contribute a dataset and propose a paradigm to quantitatively evaluate the effect of attention and KG on bag-level relation extraction (RE).
Learning from Miscellaneous Other-Class Words for Few-shot Named Entity Recognition
Few-shot Named Entity Recognition (NER) exploits only a handful of annotations to identify and classify named entity mentions.
Is Multi-Hop Reasoning Really Explainable? Towards Benchmarking Reasoning Interpretability
However, we find in experiments that many paths given by these models are actually unreasonable, while little works have been done on interpretability evaluation for them.
Flashot: A Snapshot of Flash Loan Attack on DeFi Ecosystem
Flash Loan attack can grab millions of dollars from decentralized vaults in one single transaction, drawing increasing attention from the Decentralized Finance (DeFi) players.
Learning Relation Prototype from Unlabeled Texts for Long-tail Relation Extraction
In this paper, we propose a general approach to learn relation prototypesfrom unlabeled texts, to facilitate the long-tail relation extraction by transferring knowledge from the relation types with sufficient trainingdata.
Exploring and Evaluating Attributes, Values, and Structures for Entity Alignment
GNN-based EA methods present promising performances by modeling the KG structure defined by relation triples.
Tree-Augmented Cross-Modal Encoding for Complex-Query Video Retrieval
To facilitate video retrieval with complex queries, we propose a Tree-augmented Cross-modal Encoding method by jointly learning the linguistic structure of queries and the temporal representation of videos.
Improving Event Detection via Open-domain Trigger Knowledge
Event Detection (ED) is a fundamental task in automatically structuring texts.
Expertise Style Transfer: A New Task Towards Better Communication between Experts and Laymen
The curse of knowledge can impede communication between experts and laymen.
Reinforced Negative Sampling over Knowledge Graph for Recommendation
Properly handling missing data is a fundamental challenge in recommendation.
Semi-supervised Entity Alignment via Joint Knowledge Embedding Model and Cross-graph Model
Specifically, as for the knowledge embedding model, we utilize TransE to implicitly complete two KGs towards consistency and learn relational constraints between entities.
Multi-Channel Graph Neural Network for Entity Alignment
Entity alignment typically suffers from the issues of structural heterogeneity and limited seed alignments.
Ranked #30 on
Entity Alignment
on DBP15k zh-en
Low-Resource Name Tagging Learned with Weakly Labeled Data
Name tagging in low-resource languages or domains suffers from inadequate training data.
Who, Where, and What to Wear? Extracting Fashion Knowledge from Social Media
We unify three tasks of occasion, person and clothing discovery from multiple modalities of images, texts and metadata.
Improving Neural Relation Extraction with Implicit Mutual Relations
In contrast to existing distant supervision approaches that suffer from insufficient training corpora to extract relations, our proposal of mining implicit mutual relation from the massive unlabeled corpora transfers the semantic information of entity pairs into the RE model, which is more expressive and semantically plausible.
KGAT: Knowledge Graph Attention Network for Recommendation
To provide more accurate, diverse, and explainable recommendation, it is compulsory to go beyond modeling user-item interactions and take side information into account.
Ranked #2 on
Link Prediction
on Yelp
Unifying Knowledge Graph Learning and Recommendation: Towards a Better Understanding of User Preferences
In this paper, we jointly learn the model of recommendation and knowledge graph completion.
Ranked #1 on
Knowledge Graph Completion
on MovieLens 1M
Joint Representation Learning of Cross-lingual Words and Entities via Attentive Distant Supervision
Joint representation learning of words and entities benefits many NLP tasks, but has not been well explored in cross-lingual settings.
Neural Collective Entity Linking
To address this issue, we propose a novel neural model for collective entity linking, named as NCEL.
Explainable Reasoning over Knowledge Graphs for Recommendation
Such connectivity not only reveals the semantics of entities and relations, but also helps to comprehend a user's interest.
Visually Explainable Recommendation
By this, we can not only provide recommendation results to the users, but also tell the users why an item is recommended by providing intuitive visual highlights in a personalized manner.
On Modeling Sense Relatedness in Multi-prototype Word Embedding
To enhance the expression ability of distributional word representation learning model, many researchers tend to induce word senses through clustering, and learn multiple embedding vectors for each word, namely multi-prototype word embedding model.
Bridge Text and Knowledge by Learning Multi-Prototype Entity Mention Embedding
Integrating text and knowledge into a unified semantic space has attracted significant research interests recently.
