PPaperPicks

Liang Pang

Chinese Academy of Sciences, Institute of Computing Technology, Beijing, China

46 papers at tracked venues · 36 at CORE A* · active 2024–2026

DBLP profile ↗ORCID 0000-0003-1161-8546 ↗Google Scholar ↗Homepage ↗

Venues

ACL ×9SIGIR ×8ICLR ×5WWW ×5EMNLP ×4AAAI ×3ACM MM ×3ECIR ×2SIGKDD ×2CIKM ×1CVPR ×1NAACL ×1RecSys ×1WSDM ×1

Frequent coauthors

Shicheng Xu
DBLP profile ↗ORCID search ↗
×8
Sunhao Dai
DBLP profile ↗ORCID search ↗
×7
Chen Xu
DBLP profile ↗ORCID search ↗
×4
Yuqi Zhou
DBLP profile ↗ORCID search ↗
×2
Qianchi Zhang
DBLP profile ↗ORCID search ↗
×2
Jingcheng Deng
DBLP profile ↗ORCID search ↗
×2
Minghe Gao
DBLP profile ↗ORCID search ↗
×2
Jia Gu
DBLP profile ↗ORCID search ↗
×1
Danyang Hou
DBLP profile ↗ORCID search ↗
×1
Jinwen Chen
DBLP profile ↗ORCID search ↗
×1
Zenghao Duan
DBLP profile ↗ORCID search ↗
×1
Zihao Wei
DBLP profile ↗ORCID search ↗
×1

Papers

  1. D-Models and E-Models: Diversity-Stability Trade-offs in the Sampling Behavior of Large Language Models
    WWW 2026 ·
    Jia Gu
    DBLP profile ↗ORCID search ↗
  2. Event-Aware Video Corpus Moment Retrieval
    ECIR 2026 ·
    Danyang Hou
    DBLP profile ↗ORCID search ↗
  3. Learning to Retrieve from Agent Trajectories
    SIGIR 2026 ·
    Yuqi Zhou
    DBLP profile ↗ORCID search ↗
  4. Less is More: Compact Clue Selection for Efficient Retrieval-Augmented Generation Reasoning
    WWW 2026 ·
    Qianchi Zhang
    DBLP profile ↗ORCID search ↗
  5. Privacy-Preserving Reasoning with Knowledge-Distilled Parametric Retrieval Augmented Generation
    ACL 2026 ·
    Jinwen Chen
    DBLP profile ↗ORCID search ↗
  6. Projecting Out the Malice: A Global Subspace Approach to LLM Detoxification
    ACL 2026 ·
    Zenghao Duan
    DBLP profile ↗ORCID search ↗
  7. RLKD: Distilling LLMs' Reasoning via Reinforcement Learning
    AAAI 2026 ·
    Shicheng Xu
    DBLP profile ↗ORCID search ↗
  8. Stable-RAG: Mitigating Retrieval-Permutation-Induced Hallucinations in Retrieval-Augmented Generation
    ACL 2026 ·
    Qianchi Zhang
    DBLP profile ↗ORCID search ↗
  9. The Evolution of Thought: Tracking LLM Overthinking via Reasoning Dynamics Analysis
    ACL 2026 ·
    Zihao Wei
    DBLP profile ↗ORCID search ↗
  10. Towards Quantitative Summarization Evaluation: An Integrated Atomic-Based Evaluation Framework and Dataset for Text Summarization
    ECIR 2026 ·
    Yan Lei
    DBLP profile ↗ORCID search ↗
  11. A Theory for Token-Level Harmonization in Retrieval-Augmented Generation
    ICLR 2025 ·
    Shicheng Xu
    DBLP profile ↗ORCID search ↗
  12. Bridging Jensen Gap for Max-Min Group Fairness Optimization in Recommendation
    ICLR 2025 ·
    Chen Xu
    DBLP profile ↗ORCID search ↗
  13. Cross-Modal Safety Mechanism Transfer in Large Vision-Language Models
    ICLR 2025 ·
    Shicheng Xu
    DBLP profile ↗ORCID search ↗
  14. Everything is Editable: Extend Knowledge Editing to Unstructured Data in Large Language Models
    ICLR 2025 ·
    Jingcheng Deng
    DBLP profile ↗ORCID search ↗
  15. Exploring the Escalation of Source Bias in User, Data, and Recommender System Feedback Loop
    SIGIR 2025 ·
    Yuqi Zhou
    DBLP profile ↗ORCID search ↗
  16. Following the Autoregressive Nature of LLM Embeddings via Compression and Alignment
    EMNLP 2025 ·
    Jingcheng Deng
    DBLP profile ↗ORCID search ↗
  17. Generative Ghost: Investigating Ranking Bias Hidden in AI-Generated Videos
    ACM MM 2025 ·
    Haowen Gao
    DBLP profile ↗ORCID search ↗
  18. LightPROF: A Lightweight Reasoning Framework for Large Language Model on Knowledge Graph
    AAAI 2025 ·
    Tu Ao
    DBLP profile ↗ORCID search ↗
  19. MaFeRw: Query Rewriting with Multi-Aspect Feedbacks for Retrieval-Augmented Large Language Models
    AAAI 2025 ·
    Yujing Wang
    DBLP profile ↗ORCID search ↗
  20. Media Source Matters More Than Content: Unveiling Political Bias in LLM-Generated Citations
    EMNLP 2025 ·
    Sunhao Dai
    DBLP profile ↗ORCID search ↗
  21. Mitigating Source Bias with LLM Alignment
    SIGIR 2025 ·
    Sunhao Dai
    DBLP profile ↗ORCID search ↗
  22. NExT-Search: Rebuilding User Feedback Ecosystem for Generative AI Search
    SIGIR 2025 ·
    Sunhao Dai
    DBLP profile ↗ORCID search ↗
  23. Perplexity Trap: PLM-Based Retrievers Overrate Low Perplexity Documents
    ICLR 2025 ·
    Haoyu Wang
    DBLP profile ↗ORCID search ↗
  24. The 1st Workshop on LLM Agents for Social Simulation
    CIKM 2025 ·
    Yige Yuan
    DBLP profile ↗ORCID search ↗
  25. ToolCoder: A Systematic Code-Empowered Tool Learning Framework for Large Language Models
    ACL 2025 ·
    Hanxing Ding
    DBLP profile ↗ORCID search ↗
  26. Understanding Accuracy-Fairness Trade-offs in Re-ranking through Elasticity in Economics
    SIGIR 2025 ·
    Chen Xu
    DBLP profile ↗ORCID search ↗
  27. Unifying Bias and Unfairness in Information Retrieval: New Challenges in the LLM Era
    WSDM 2025 ·
    Sunhao Dai
    DBLP profile ↗ORCID search ↗
  28. Unveiling Knowledge Boundary of Large Language Models for Trustworthy Information Access
    SIGIR 2025 ·
    Yang Deng
    DBLP profile ↗ORCID search ↗
  29. A Study of Implicit Ranking Unfairness in Large Language Models
    EMNLP 2024 ·
    Chen Xu
    DBLP profile ↗ORCID search ↗
  30. A Taxation Perspective for Fair Re-ranking
    SIGIR 2024 ·
    Chen Xu
    DBLP profile ↗ORCID search ↗
  31. Beyond Memorization: The Challenge of Random Memory Access in Language Models
    ACL 2024 ·
    Tongyao Zhu
    DBLP profile ↗ORCID search ↗
  32. Bias and Unfairness in Information Retrieval Systems: New Challenges in the LLM Era
    SIGKDD 2024 ·
    Sunhao Dai
    DBLP profile ↗ORCID search ↗
  33. Can Small Language Models be Good Reasoners for Sequential Recommendation?
    WWW 2024 ·
    Yuling Wang
    DBLP profile ↗ORCID search ↗
  34. Cocktail: A Comprehensive Information Retrieval Benchmark with LLM-Generated Documents Integration
    ACL 2024 ·
    Sunhao Dai
    DBLP profile ↗ORCID search ↗
  35. De-fine: Decomposing and Refining Visual Programs with Auto-Feedback
    ACM MM 2024 ·
    Minghe Gao
    DBLP profile ↗ORCID search ↗
  36. Enhancing Training Data Attribution for Large Language Models with Fitting Error Consideration
    EMNLP 2024 ·
    Kangxi Wu
    DBLP profile ↗ORCID search ↗
  37. Fact : Teaching MLLMs with Faithful, Concise and Transferable Rationales
    ACM MM 2024 ·
    Minghe Gao
    DBLP profile ↗ORCID search ↗
  38. HalluciDoctor: Mitigating Hallucinatory Toxicity in Visual Instruction Data
    CVPR 2024 ·
    Qifan Yu
    DBLP profile ↗ORCID search ↗
  39. Information-Controllable Graph Contrastive Learning for Recommendation
    RecSys 2024 ·
    Zirui Guo
    DBLP profile ↗ORCID search ↗
  40. Invisible Relevance Bias: Text-Image Retrieval Models Prefer AI-Generated Images
    SIGIR 2024 ·
    Shicheng Xu
    DBLP profile ↗ORCID search ↗
  41. List-aware Reranking-Truncation Joint Model for Search and Retrieval-augmented Generation
    WWW 2024 ·
    Shicheng Xu
    DBLP profile ↗ORCID search ↗
  42. Neural Retrievers are Biased Towards LLM-Generated Content
    SIGKDD 2024 ·
    Sunhao Dai
    DBLP profile ↗ORCID search ↗
  43. Plot Retrieval as an Assessment of Abstract Semantic Association
    ACL 2024 ·
    Shicheng Xu
    DBLP profile ↗ORCID search ↗
  44. Search-in-the-Chain: Interactively Enhancing Large Language Models with Search for Knowledge-intensive Tasks
    WWW 2024 ·
    Shicheng Xu
    DBLP profile ↗ORCID search ↗
  45. Think Before You Speak: Cultivating Communication Skills of Large Language Models via Inner Monologue
    NAACL 2024 ·
    Junkai Zhou
    DBLP profile ↗ORCID search ↗
  46. Unsupervised Information Refinement Training of Large Language Models for Retrieval-Augmented Generation
    ACL 2024 ·
    Shicheng Xu
    DBLP profile ↗ORCID search ↗