Pengfei Cao

Bias-Restrained Prefix Representation Finetuning for Mathematical Reasoning AAAI 2026 Do LLMs Know Tool Irrelevance? Demystifying Structural Alignment Bias in Tool Invocations ACL 2026 Empowering GUI Agents via Autonomous Experience Exploration and Hindsight Experience Utilization for Task Planning ACL 2026 Look Light, Think Heavy: What Multimodal Chain-of-Thought Reasoning Can and Cannot Do ACL 2026 SemEval-2026 Task 12: Abductive Event Reasoning: Towards Real-World Event Causal Inference for Large Language Models SemEval 2026 Agent-RewardBench: Towards a Unified Benchmark for Reward Modeling across Perception, Planning, and Safety in Real-World Multimodal Agents ACL 2025 A Troublemaker with Contagious Jailbreak Makes Chaos in Honest Towns ACL 2025 Beyond Under-Alignment: Atomic Preference Enhanced Factuality Tuning for Large Language Models NAACL 2025 CITI: Enhancing Tool Utilizing Ability in Large Language Models Without Sacrificing General Performance AAAI 2025 Cracking Factual Knowledge: A Comprehensive Analysis of Degenerate Knowledge Neurons in Large Language Models ACL 2025 DTELS: Towards Dynamic Granularity of Timeline Summarization NAACL 2025 Evaluating Personalized Tool-Augmented LLMs from the Perspectives of Personalization and Proactivity ACL 2025 Knowledge in Superposition: Unveiling the Failures of Lifelong Knowledge Editing for Large Language Models AAAI 2025 Knowledge Localization: Mission Not Accomplished? Enter Query Localization! ICLR 2025 Know-MRI: A Knowledge Mechanisms Revealer&Interpreter for Large Language Models ACL 2025 M2Edit: Locate and Edit Multi-Granularity Knowledge in Multimodal Large Language Model EMNLP 2025 MIRAGE: Evaluating and Explaining Inductive Reasoning Process in Language Models ICLR 2025 RAG-RewardBench: Benchmarking Reward Models in Retrieval Augmented Generation for Preference Alignment ACL 2025 Revealing the Deceptiveness of Knowledge Editing: A Mechanistic Analysis of Superficial Editing ACL 2025 The Knowledge Microscope: Features as Better Analytical Lenses than Neurons ACL 2025 Towards Better Chain-of-Thought: A Reflection on Effectiveness and Faithfulness ACL 2025 Towards Robust Knowledge Unlearning: An Adversarial Framework for Assessing and Improving Unlearning Robustness in Large Language Models AAAI 2025 AgentsCourt: Building Judicial Decision-Making Agents with Court Debate Simulation and Legal Knowledge Augmentation EMNLP 2024 Continual Few-shot Event Detection via Hierarchical Augmentation Networks COLING 2024 Cutting Off the Head Ends the Conflict: A Mechanism for Interpreting and Mitigating Knowledge Conflicts in Language Models ACL 2024 Focus on Your Question! Interpreting and Mitigating Toxic CoT Problems in Commonsense Reasoning ACL 2024 Journey to the Center of the Knowledge Neurons: Discoveries of Language-Independent Knowledge Neurons and Degenerate Knowledge Neurons AAAI 2024 Leros: Learning Explicit Reasoning on Synthesized Data for Commonsense Question Answering COLING 2024 LINKED: Eliciting, Filtering and Integrating Knowledge in Large Language Model for Commonsense Reasoning EMNLP 2024 MULFE: A Multi-Level Benchmark for Free Text Model Editing ACL 2024 Oasis: Data Curation and Assessment System for Pretraining of Large Language Models IJCAI 2024 RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language Models NeurIPS 2024 Tug-of-War between Knowledge: Exploring and Resolving Knowledge Conflicts in Retrieval-Augmented Language Models COLING 2024 Unlocking the Future: Exploring Look-Ahead Planning Mechanistic Interpretability in Large Language Models EMNLP 2024 Whispers that Shake Foundations: Analyzing and Mitigating False Premise Hallucinations in Large Language Models EMNLP 2024 WilKE: Wise-Layer Knowledge Editor for Lifelong Knowledge Editing ACL 2024 Zero-Shot Cross-Lingual Document-Level Event Causality Identification with Heterogeneous Graph Contrastive Transfer Learning COLING 2024 ZhuJiu-Knowledge: A Fairer Platform for Evaluating Multiple Knowledge Types in Large Language Models NAACL 2024 Alignment Precedes Fusion: Open-Vocabulary Named Entity Recognition as Context-Type Semantic Matching EMNLP 2023 Complex Event Schema Induction with Knowledge-Enriched Diffusion Model EMNLP 2023 DiffusionSL: Sequence Labeling via Tag Diffusion Process EMNLP 2023 Event Ontology Completion with Hierarchical Structure Evolution Networks EMNLP 2023 InstructoR: Instructing Unsupervised Conversational Dense Retrieval with Large Language Models EMNLP 2023 LEGO: A Multi-agent Collaborative Framework with Role-playing and Iterative Feedback for Causality Explanation Generation EMNLP 2023 Zero-Shot Cross-Lingual Event Argument Extraction with Language-Oriented Prefix-Tuning AAAI 2023 ZhuJiu: A Multi-dimensional, Multi-faceted Chinese Benchmark for Large Language Models EMNLP 2023 A Good Neighbor, A Found Treasure: Mining Treasured Neighbors for Knowledge Graph Entity Typing EMNLP 2022 CogKTR: A Knowledge-Enhanced Text Representation Toolkit for Natural Language Understanding EMNLP 2022 Automatic ICD Coding via Interactive Shared Representation Networks with Self-distillation Mechanism ACL 2021 Domain-Lifelong Learning for Dialogue State Tracking via Knowledge Preservation Networks EMNLP 2021 Improving Event Causality Identification via Self-Supervised Representation Learning on External Causal Statement ACL 2021 Knowledge-Enriched Event Causality Identification via Latent Structure Induction Networks ACL 2021 LearnDA: Learnable Knowledge-Guided Data Augmentation for Event Causality Identification ACL 2021 Uncertain Local-to-Global Networks for Document-Level Event Factuality Identification EMNLP 2021 Clinical-Coder: Assigning Interpretable ICD-10 Codes to Chinese Clinical Notes ACL 2020 HyperCore: Hyperbolic and Co-graph Representation for Automatic ICD Coding ACL 2020 Incremental Event Detection via Knowledge Consolidation Networks EMNLP 2020 Adversarial Transfer Learning for Chinese Named Entity Recognition with Self-Attention Mechanism EMNLP 2018