PPaperPicks

Yiqun Liu

Tsinghua University, Department of Computer Science and Technology, Beijing, China

54 papers at tracked venues · 44 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. Analytical Search
  2. Auto-PRE: An Automatic and Cost-Efficient Peer-Review Framework for Language Generation Evaluation
  3. Beyond Experience Retrieval: Learning to Generate Utility-Optimized Structured Experience for Frozen LLMs
  4. Chinese Court Simulation with LLM-Based Agents System
  5. Enhancing Judgment Document Generation via Agentic Legal Information Collection and Rubric-Guided Optimization
  6. Equity vs. Equality: Optimizing Ranking Fairness for Tailored Provider Needs
  7. Generalized Pseudo-Relevance Feedback
  8. Investigating Prosocial Behavior Theory in LLM Agents Under Policy-Induced Inequities
  9. Joint Evaluation of Answer and Reasoning Consistency for Hallucination Detection in Large Reasoning Models
  10. LegalKit: A Modular Toolkit for Efficient Legal AI Evaluation
  11. Simulating Dispute Mediation with LLM-Based Agents for Legal Research
  12. SurGE: A Benchmark and Evaluation Framework for Scientific Survey Generation
  13. TEC: A Collection of Human Trial-and-error Trajectories for Problem Solving
  14. TwinVoice: A Multi-dimensional Benchmark Towards Digital Twins via LLM Persona Simulation
  15. Unsupervised Dense Retrieval with Conterfactual Contrastive Learning
  16. Augmenting Multi-Agent Communication with State Delta Trajectory
  17. BLADE: Enhancing Black-Box Large Language Models with Small Domain-Specific Models
  18. Brain Image Reconstruction with Retrieval-Augmented Diffusion
  19. CalibraEval: Calibrating Prediction Distribution to Mitigate Selection Bias in LLMs-as-Judges
  20. DELTA: Pre-Train a Discriminative Encoder for Legal Case Retrieval via Structural Word Alignment
  21. Decoupling Knowledge and Context: An Efficient and Effective Retrieval Augmented Generation Framework via Cross Attention
  22. Decoupling Reasoning and Knowledge Injection for In-Context Knowledge Editing
  23. Dynamic and Parametric Retrieval-Augmented Generation
  24. JuDGE: Benchmarking Judgment Document Generation for Chinese Legal System
  25. JustEva: A Toolkit to Evaluate LLM Fairness in Legal Knowledge Inference
  26. Knowledge Editing through Chain-of-Thought
  27. Learning LLM-as-a-Judge for Preference Alignment
  28. LegalAgentBench: Evaluating LLM Agents in Legal Domain
  29. LexRAG: Benchmarking Retrieval-Augmented Generation in Multi-Turn Legal Consultation Conversation
  30. Parametric Retrieval Augmented Generation
  31. Qilin: A Multimodal Information Retrieval Dataset with APP-level User Sessions
  32. Robust Fine-tuning for Retrieval Augmented Generation against Retrieval Defects
  33. SelfRACG: Enabling LLMs to Self-Express and Retrieve for Code Generation
  34. SimVBG: Simulating Individual Values by Backstory Generation
  35. The 1st NIP@IR Workshop on New Interaction Paradigms for Information Retrieval in the Era of Generative AI
  36. Understanding the Effect of Opinion Polarization in Short Video Browsing
  37. Automatic Large Language Model Evaluation via Peer Review
  38. Capability-aware Prompt Reformulation Learning for Text-to-Image Generation
  39. Combining Multiple Supervision for Robust Zero-Shot Dense Retrieval
  40. DRAGIN: Dynamic Retrieval Augmented Generation based on the Real-time Information Needs of Large Language Models
  41. EEG-SVRec: An EEG Dataset with User Multidimensional Affective Engagement Labels in Short Video Recommendation
  42. GNN4EEG: A Benchmark and Toolkit for Electroencephalography Classification with Graph Neural Network
  43. LeCaRDv2: A Large-Scale Chinese Legal Case Retrieval Dataset
  44. LeDQA: A Chinese Legal Case Document-based Question Answering Dataset
  45. LexEval: A Comprehensive Chinese Legal Benchmark for Evaluating Large Language Models
  46. Probabilistic Attention for Sequential Recommendation
  47. Prompt Refinement with Image Pivot for Text-to-Image Generation
  48. Query Augmentation with Brain Signals
  49. STARD: A Chinese Statute Retrieval Dataset Derived from Real-life Queries by Non-professionals
  50. Scaling Laws For Dense Retrieval
  51. Sequential Recommendation with Latent Relations based on Large Language Model
  52. Unsupervised Large Language Model Alignment for Information Retrieval via Contrastive Feedback
  53. Unsupervised Real-Time Hallucination Detection based on the Internal States of Large Language Models
  54. Wikiformer: Pre-training with Structured Information of Wikipedia for Ad-Hoc Retrieval