Pengfei Cao

Venues

Frequent coauthors

Papers

1. Bias-Restrained Prefix Representation Finetuning for Mathematical Reasoning
   AAAI 2026 ·

   Sirui Liang

   DBLP profile ↗ORCID search ↗
2. Do LLMs Know Tool Irrelevance? Demystifying Structural Alignment Bias in Tool Invocations
   ACL 2026 ·

   Yilong Liu

   DBLP profile ↗ORCID search ↗
3. Empowering GUI Agents via Autonomous Experience Exploration and Hindsight Experience Utilization for Task Planning
   ACL 2026 ·

   Tianyi Men

   DBLP profile ↗ORCID search ↗
4. From Signal Degradation to Computation Collapse: Uncovering the Two Failure Modes of LLM Quantization
   ACL 2026 ·

   Chenxi Zhou

   DBLP profile ↗ORCID search ↗
5. Learning How to Remember: A Meta-Cognitive Management Method for Structured and Transferable Agent Memory
   ACL 2026 ·

   Sirui Liang

   DBLP profile ↗ORCID search ↗
6. Lightweight Haar Wavelet Subband Pruning for LLMs
   ACL 2026 ·

   Jiang Li

   DBLP profile ↗ORCID search ↗
7. Look Light, Think Heavy: What Multimodal Chain-of-Thought Reasoning Can and Cannot Do
   ACL 2026 ·

   Zhuoran Jin

   DBLP profile ↗ORCID search ↗
8. Task-Stratified Knowledge Scaling Laws for Post-Training Quantized Large Language Models
   ACL 2026 ·

   Chenxi Zhou

   DBLP profile ↗ORCID search ↗
9. A Troublemaker with Contagious Jailbreak Makes Chaos in Honest Towns
   ACL 2025 ·

   Tianyi Men

   DBLP profile ↗ORCID search ↗
10. Agent-RewardBench: Towards a Unified Benchmark for Reward Modeling across Perception, Planning, and Safety in Real-World Multimodal Agents
    ACL 2025 ·

    Tianyi Men

    DBLP profile ↗ORCID search ↗
11. Beyond Under-Alignment: Atomic Preference Enhanced Factuality Tuning for Large Language Models
    NAACL 2025 ·

    Hongbang Yuan

    DBLP profile ↗ORCID search ↗
12. CITI: Enhancing Tool Utilizing Ability in Large Language Models Without Sacrificing General Performance
    AAAI 2025 ·

    Yupu Hao

    DBLP profile ↗ORCID search ↗
13. Cracking Factual Knowledge: A Comprehensive Analysis of Degenerate Knowledge Neurons in Large Language Models
    ACL 2025 ·

    Yuheng Chen

    DBLP profile ↗ORCID search ↗
14. DTELS: Towards Dynamic Granularity of Timeline Summarization
    NAACL 2025 ·

    Chenlong Zhang

    DBLP profile ↗ORCID search ↗
15. Evaluating Personalized Tool-Augmented LLMs from the Perspectives of Personalization and Proactivity
    ACL 2025 ·

    Yupu Hao

    DBLP profile ↗ORCID search ↗
16. Know-MRI: A Knowledge Mechanisms Revealer&Interpreter for Large Language Models
    ACL 2025 ·

    Jiaxiang Liu

    DBLP profile ↗ORCID search ↗
17. Knowledge Localization: Mission Not Accomplished? Enter Query Localization!
    ICLR 2025 ·

    Yuheng Chen

    DBLP profile ↗ORCID search ↗
18. Knowledge in Superposition: Unveiling the Failures of Lifelong Knowledge Editing for Large Language Models
    AAAI 2025 ·

    Chenhui Hu

    DBLP profile ↗ORCID search ↗
19. M2Edit: Locate and Edit Multi-Granularity Knowledge in Multimodal Large Language Model
    EMNLP 2025 ·

    Yang Zhou

    DBLP profile ↗ORCID search ↗
20. MIRAGE: Evaluating and Explaining Inductive Reasoning Process in Language Models
    ICLR 2025 ·

    Jiachun Li

    DBLP profile ↗ORCID search ↗
21. RAG-RewardBench: Benchmarking Reward Models in Retrieval Augmented Generation for Preference Alignment
    ACL 2025 ·

    Zhuoran Jin

    DBLP profile ↗ORCID search ↗
22. Revealing the Deceptiveness of Knowledge Editing: A Mechanistic Analysis of Superficial Editing
    ACL 2025 ·

    Jiakuan Xie

    DBLP profile ↗ORCID search ↗
23. The Knowledge Microscope: Features as Better Analytical Lenses than Neurons
    ACL 2025 ·

    Yuheng Chen

    DBLP profile ↗ORCID search ↗
24. Towards Better Chain-of-Thought: A Reflection on Effectiveness and Faithfulness
    ACL 2025 ·

    Jiachun Li

    DBLP profile ↗ORCID search ↗
25. Towards Robust Knowledge Unlearning: An Adversarial Framework for Assessing and Improving Unlearning Robustness in Large Language Models
    AAAI 2025 ·

    Hongbang Yuan

    DBLP profile ↗ORCID search ↗
26. AgentsCourt: Building Judicial Decision-Making Agents with Court Debate Simulation and Legal Knowledge Augmentation
    EMNLP 2024 ·

    Zhitao He

    DBLP profile ↗ORCID search ↗
27. Cutting Off the Head Ends the Conflict: A Mechanism for Interpreting and Mitigating Knowledge Conflicts in Language Models
    ACL 2024 ·

    Zhuoran Jin

    DBLP profile ↗ORCID search ↗
28. Focus on Your Question! Interpreting and Mitigating Toxic CoT Problems in Commonsense Reasoning
    ACL 2024 ·

    Jiachun Li

    DBLP profile ↗ORCID search ↗
29. Journey to the Center of the Knowledge Neurons: Discoveries of Language-Independent Knowledge Neurons and Degenerate Knowledge Neurons
    AAAI 2024 ·

    Yuheng Chen

    DBLP profile ↗ORCID search ↗
30. LINKED: Eliciting, Filtering and Integrating Knowledge in Large Language Model for Commonsense Reasoning
    EMNLP 2024 ·

    Jiachun Li

    DBLP profile ↗ORCID search ↗
31. MULFE: A Multi-Level Benchmark for Free Text Model Editing
    ACL 2024 ·

    Chenhao Wang

    DBLP profile ↗ORCID search ↗
32. Oasis: Data Curation and Assessment System for Pretraining of Large Language Models
    IJCAI 2024 ·

    Tong Zhou

    DBLP profile ↗ORCID search ↗
33. RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language Models
    NeurIPS 2024 ·

    Zhuoran Jin

    DBLP profile ↗ORCID search ↗
34. Unlocking the Future: Exploring Look-Ahead Planning Mechanistic Interpretability in Large Language Models
    EMNLP 2024 ·

    Tianyi Men

    DBLP profile ↗ORCID search ↗
35. Whispers that Shake Foundations: Analyzing and Mitigating False Premise Hallucinations in Large Language Models
    EMNLP 2024 ·

    Hongbang Yuan

    DBLP profile ↗ORCID search ↗
36. WilKE: Wise-Layer Knowledge Editor for Lifelong Knowledge Editing
    ACL 2024 ·

    Chenhui Hu

    DBLP profile ↗ORCID search ↗
37. ZhuJiu-Knowledge: A Fairer Platform for Evaluating Multiple Knowledge Types in Large Language Models
    NAACL 2024 ·

    Pengfan Du

    DBLP profile ↗ORCID search ↗