PPaperPicks

Zhicheng Dou

Renmin University of China, Beijing, China

98 papers at tracked venues · 78 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. ATIR: Towards Audio-Text Interleaved Contextual Retrieval
  2. Agentic-R: Learning to Retrieve for Agentic Search
  3. DeepAgent: A General Reasoning Agent with Scalable Toolsets
  4. ET-Agent: Incentivizing Effective Tool-Integrated Reasoning Agent via Behavior Calibration
  5. EnvScaler: Scaling Tool-Interactive Environments for LLM Agent via Programmatic Synthesis
  6. Evaluating the Factuality of Large Language Models Using Multiple Plug-and-Play Fact Sources
  7. FinSight: Towards Real-World Financial Deep Research
  8. GLARE: Agentic Reasoning for Legal Judgment Prediction
  9. HiRA: Decoupling Planning and Execution with Hierarchical Reasoning in Deep Search
  10. HierSearch: A Hierarchical Enterprise Deep Search Framework Integrating Local and Web Searches
  11. Internalizing Explicit Reasoning into Latent Space for Dense Retrieval
  12. LLM-Generated Text May Harm Your Retrieval! A Robust Detection Strategy for Retrieval-Augmented Generation
  13. Memory Matters More: Event-Centric Memory as a Logic Map for Agent Searching and Reasoning
  14. MoCa: Modality-aware Continual Pre-training Makes Better Bidirectional Multimodal Embeddings
  15. PaperScope: A Multi-Modal Multi-Document Benchmark for Agentic Deep Research Across Massive Scientific Papers
  16. RLSeek: Evidence-Grounded Reasoning for RAG Hallucination Detection
  17. ReasonRank: Empowering Passage Ranking with Strong Reasoning Ability
  18. Reasoning-Aware AIGC Detection via Alignment and Reinforcement
  19. R⌃3AG: Retriever Routing for Retrieval-Augmented Generation
  20. SmartSearch: Process Reward-Guided Query Refinement for Search Agents
  21. TimelineReasoner: Advancing Timeline Summarization with Large Reasoning Models
  22. Tool-Star: Empowering Multi-Tool Collaborative Web Agent via Reinforcement Learning
  23. ToolScope: An Agentic Framework for Vision-Guided and Long-Horizon Tool Use
  24. Toward Generalized Web Agent Training: A Deep Dive into Entropy-Balanced Reinforcement Learning
  25. Towards Mixed-Modal Retrieval for Universal Retrieval-Augmented Generation
  26. Web Sitemap Knowledge Can Enhance Autonomous Browsing
  27. e5-omni: Explicit Cross-modal Alignment for Omni-modal Embeddings
  28. A Non-Contrastive Learning Framework for Sequential Recommendation with Preference-Preserving Profile Generation
  29. A Silver Bullet or a Compromise for Full Attention? A Comprehensive Study of Gist Token-based Context Compression
  30. Boosting Long-Context Information Seeking via Query-Guided Activation Refilling
  31. CORAL: Benchmarking Multi-turn Conversational Retrieval-Augmented Generation
  32. Chain-of-Retrieval Augmented Generation
  33. ClariLM: Enhancing Open-domain Clarification Ability for Large Language Models
  34. CoRanking: Collaborative Ranking with Small and Large Ranking Agents
  35. Collaborative Optimization Approach for Workflow Agents in User Behavior Modeling
  36. DIVAgent: A Diversified Search Agent that Mimics the Human Search Process
  37. Defending against Indirect Prompt Injection by Instruction Detection
  38. Descriptive and Discriminative Document Identifiers for Generative Retrieval
  39. Embedding Prior Task-specific Knowledge into Language Models for Context-aware Document Ranking
  40. Enhancing LLM Text Detection with Retrieved Contexts and Logits Distribution Consistency
  41. Evolving Graph-Based Context Modeling for Multi-Turn Conversational Retrieval-Augmented Generation
  42. FairDiverse: A Comprehensive Toolkit for Fairness- and Diversity-aware Information Retrieval
  43. FlashRAG: A Modular Toolkit for Efficient Retrieval-Augmented Generation Research
  44. FollowGPT: A Framework of Follow-up Question Generation for Large Language Models via Conversation Log Mining
  45. HawkBench: Investigating Resilience of RAG Methods on Stratified Information-Seeking Tasks
  46. Hierarchical Document Refinement for Long-context Retrieval-augmented Generation
  47. HtmlRAG: HTML is Better Than Plain Text for Modeling Retrieved Knowledge in RAG Systems
  48. LLMs + Persona-Plug = Personalized LLMs
  49. Little Giants: Synthesizing High-Quality Embedding Data at Scale
  50. Long Context Compression with Activation Beacon
  51. MemoRAG: Boosting Long Context Processing with Global Memory-Enhanced Retrieval Augmentation
  52. MomentSeeker: A Task-Oriented Benchmark For Long-Video Moment Retrieval
  53. Neuro-Symbolic Query Compiler
  54. OmniEval: An Omnidirectional and Automatic RAG Evaluation Benchmark in Financial Domain
  55. One Token Can Help! Learning Scalable and Pluggable Virtual Tokens for Retrieval-Augmented Large Language Models
  56. P3: Prompts Promote Prompting
  57. Progressive Multimodal Reasoning via Active Retrieval
  58. RAG-Critic: Leveraging Automated Critic-Guided Agentic Workflow for Retrieval Augmented Generation
  59. Retrieving Intent-covering Demonstrations for Clarification Generation in Conversational Search Systems
  60. RetroLLM: Empowering Large Language Models to Retrieve Fine-grained Evidence within Generation
  61. Search-o1: Agentic Search-Enhanced Large Reasoning Models
  62. Single LLM, Multiple Roles: A Unified Retrieval-Augmented Generation Framework Using Role-Specific Token Optimization
  63. Sliding Windows Are Not the End: Exploring Full Ranking with Long-Context Large Language Models
  64. Tackling the Length Barrier: Dynamic Context Browsing for Knowledge-Intensive Task
  65. TimeRAG: Enhancing Complex Temporal Reasoning with Search Engine Augmentation
  66. Toward Verifiable Instruction-Following Alignment for Retrieval Augmented Generation
  67. Towards Effective and Efficient Continual Pre-training of Large Language Models
  68. Understand What LLM Needs: Dual Preference Alignment for Retrieval-Augmented Generation
  69. UniGist: Towards General and Hardware-aligned Sequence-level Long Context Compression
  70. Value Compass Benchmarks: A Comprehensive, Generative and Self-Evolving Platform for LLMs' Value Evaluation
  71. WebThinker: Empowering Large Reasoning Models with Deep Research Capability
  72. mmE5: Improving Multimodal Multilingual Embeddings via High-quality Synthetic Data
  73. A Multi-Task Embedder For Retrieval Augmented LLMs
  74. An Element is Worth a Thousand Words: Enhancing Legal Case Retrieval by Incorporating Legal Elements
  75. BIDER: Bridging Knowledge Inconsistency for Efficient Retrieval-Augmented LLMs via Key Supporting Evidence
  76. Boosting the Potential of Large Language Models with an Intelligent Information Assistant
  77. CL4DIV: A Contrastive Learning Framework for Search Result Diversification
  78. ChatRetriever: Adapting Large Language Models for Generalized and Robust Conversational Dense Retrieval
  79. Cognitive Personalized Search Integrating Large Language Models with an Efficient Memory Mechanism
  80. CorpusLM: Towards a Unified Language Model on Corpus for Knowledge-Intensive Tasks
  81. Enabling Discriminative Reasoning in LLMs for Legal Judgment Prediction
  82. Enhancing Multi-field B2B Cloud Solution Matching via Contrastive Pre-training
  83. Generalizing Conversational Dense Retrieval via LLM-Cognition Data Augmentation
  84. Generating Intent-aware Clarifying Questions in Conversational Information Retrieval Systems
  85. Generating Multi-turn Clarification for Web Information Seeking
  86. Generative Retrieval via Term Set Generation
  87. Grounding Language Model with Chunking-Free In-Context Retrieval
  88. INTERS: Unlocking the Power of Large Language Models in Search with Instruction Tuning
  89. Information Retrieval Meets Large Language Models
  90. Interpreting Conversational Dense Retrieval by Rewriting-Enhanced Inversion of Session Embedding
  91. JDivPS: A Diversified Product Search Dataset
  92. Learning Dynamic Multi-attribute Interest for Personalized Product Search
  93. Learning Interpretable Legal Case Retrieval via Knowledge-Guided Case Reformulation
  94. Metacognitive Retrieval-Augmented Large Language Models
  95. Mining Exploratory Queries for Conversational Search
  96. RAG-Studio: Towards In-Domain Adaptation of Retrieval Augmented Generation Through Self-Alignment
  97. Small Models, Big Insights: Leveraging Slim Proxy Models To Decide When and What to Retrieve for LLMs
  98. UniGen: A Unified Generative Framework for Retrieval and Question Answering with Large Language Models