PPaperPicks

Pengjie Ren

33 papers at tracked venues · 20 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. Model Editing for New Document Integration in Generative Information Retrieval
  2. Spectral Characterization and Mitigation of Sequential Knowledge Editing Collapse
  3. Belief-Calibrated Multi-Agent Consensus Seeking for Complex NLP Tasks
  4. Bridging the Capability Gap: Joint Alignment Tuning for Harmonizing LLM-based Multi-Agent Systems
  5. Constrained Auto-Regressive Decoding Constrains Generative Retrieval
  6. ExcluIR: Exclusionary Neural Information Retrieval
  7. Improving Sequential Recommenders through Counterfactual Augmentation of System Exposure
  8. Integrating Learning-Based Manipulation and Physics-Based Locomotion for Whole-Body Badminton Robot Control
  9. KELE: Residual Knowledge Erasure for Enhanced Multi-hop Reasoning in Knowledge Editing
  10. MACPO: Weak-to-Strong Alignment via Multi-Agent Contrastive Preference Optimization
  11. Malevolence Attacks Against Pretrained Dialogue Models
    ECIR 2025 · Pengjie Ren
  12. Offline Trajectory Optimization for Offline Reinforcement Learning
  13. Replication and Exploration of Generative Retrieval over Dynamic Corpora
  14. Retrieval Models Aren't Tool-Savvy: Benchmarking Tool Retrieval for Large Language Models
  15. Triplet Contrastive Learning with Learnable Sequence Augmentation for Sequential Recommendation
  16. Trustworthy Medical Question Answering: An Evaluation-Centric Survey
  17. UIPE: Enhancing LLM Unlearning by Removing Knowledge Related to Forgetting Targets
  18. Uncovering Overfitting in Large Language Model Editing
  19. Autonomous Workflow for Multimodal Fine-Grained Training Assistants Towards Mixed Reality
  20. Confucius: Iterative Tool Learning from Introspection Feedback by Easy-to-Difficult Curriculum
  21. Content-Based Collaborative Generation for Recommender Systems
  22. Debiasing Sequential Recommenders through Distributionally Robust Optimization over System Exposure
  23. Generate-then-Ground in Retrieval-Augmented Generation for Multi-hop Question Answering
  24. Generative News Recommendation
  25. Generative Retrieval as Multi-Vector Dense Retrieval
  26. KnowTuning: Knowledge-aware Fine-tuning for Large Language Models
  27. Knowledge Graph Enhanced Large Language Model Editing
  28. Learning to Use Tools via Cooperative and Interactive Agents
  29. MEFT: Memory-Efficient Fine-Tuning through Sparse Adapter
  30. MELoRA: Mini-Ensemble Low-Rank Adapters for Parameter-Efficient Fine-Tuning
    ACL 2024 · Pengjie Ren
  31. On the Effectiveness of Unlearning in Session-Based Recommendation
  32. Self-Supervised Position Debiasing for Large Language Models
  33. Towards Empathetic Conversational Recommender Systems