Lune

Profiles2020-2026

Hongyu Lin

Chinese Information Processing Laboratory, Institute of Software, Chinese Academy of Sciences

43Papers
0Last author
82Unique co-authors
1First author
0Solo

First and last author come from byline position, which some venues assign alphabetically.

Recent papers43

  1. DeepRAG: Thinking to Retrieve Step by Step for Large Language ModelsAuthor 6 of 9ICLR 2026 · 30 citations
  2. PaperRegister: Boosting Flexible-grained Paper Search via Hierarchical Register IndexingAuthor 3 of 8ACL 2026 · 1 citation
  3. All Languages Matter: Understanding and Mitigating Language Bias in Multilingual RAGAuthor 9 of 12ACL 2026
  4. Does Question Really Matter? The Attribution of Answer Bias in LLM EvaluationAuthor 3 of 5AAAI 2026
  5. Knowing When to Quit: Diagnosing and Training LLMs to Abort Futile ReasoningAuthor 5 of 8ACL Findings 2026
  6. On the Editability of Delta Parameters in Post-Trained ModelsAuthor 4 of 8ACL Findings 2026
  7. Towards Multimodal Large Language Models with Both Training and Inference EfficiencyAuthor 4 of 7ICML 2026
  8. CRUXEVAL-X: A Benchmark for Multilingual Code Reasoning, Understanding and ExecutionAuthor 5 of 9ACL 2025 · 26 citations
  9. DOMAINEVAL: An Auto-Constructed Benchmark for Multi-Domain Code GenerationAuthor 4 of 7AAAI 2025 · 25 citations
  10. DeepSolution: Boosting Complex Engineering Solution Design via Tree-based Exploration and Bi-point ThinkingAuthor 4 of 9ACL 2025 · 13 citations
  11. Critic-CoT: Boosting the Reasoning Abilities of Large Language Model via Chain-of-Thought CriticAuthor 6 of 10ACL Findings 2025 · 4 citations
  12. On-Policy Self-Alignment with Fine-grained Knowledge Feedback for Hallucination MitigationAuthor 7 of 11ACL Findings 2025 · 3 citations
  13. Sparse Latents Steer Retrieval-Augmented GenerationAuthor 8 of 10ACL 2025 · 2 citations
  14. Rethinking Reward Model Evaluation: Are We Barking up the Wrong Tree?Author 4 of 10ICLR 2025
  15. Teach Small Models to Reason by Curriculum DistillationAuthor 3 of 5EMNLP 2025
  16. Benchmarking Large Language Models in Retrieval-Augmented GenerationAuthor 2 of 4AAAI 2024 · 531 citations
  17. Mitigating Large Language Model Hallucinations via Autonomous Knowledge Graph-Based RetrofittingAuthor 3 of 7AAAI 2024 · 127 citations
  18. Self-Retrieval: End-to-End Information Retrieval with One Large Language ModelAuthor 8 of 13NeurIPS 2024 · 14 citations
  19. Spiral of Silence: How is Large Language Model Killing Information Retrieval? - A Case Study on Open Domain Question AnsweringAuthor 3 of 8ACL 2024 · 8 citations
  20. Not All Contexts Are Equal: Teaching LLMs Credibility-aware GenerationAuthor 3 of 8EMNLP 2024 · 4 citations
  21. REInstruct: Building Instruction Data from Unlabeled CorpusAuthor 4 of 6ACL Findings 2024 · 3 citations
  22. Chain-of-Rewrite: Aligning Question and Documents for Open-Domain Question AnsweringAuthor 3 of 9EMNLP Findings 2024 · 1 citation
  23. Rule or Story, Which is a Better Commonsense Expression for Talking with Large Language Models?Author 3 of 6ACL 2024 · 1 citation
  24. Seg2Act: Global Context-aware Action Generation for Document Logical StructuringAuthor 6 of 9EMNLP 2024 · 1 citation
  25. SoFA: Shielded On-the-fly Alignment via Priority Rule FollowingAuthor 4 of 8ACL Findings 2024
  26. Universal Information Extraction as Unified Semantic MatchingAuthor 5 of 8AAAI 2023 · 96 citations
  27. Learning In-context Learning for Named Entity RecognitionAuthor 3 of 10ACL 2023 · 29 citations
  28. Dialogue Rewriting via Skeleton-Guided GenerationAuthor 2 of 9AAAI 2023 · 2 citations
  29. Ambiguous Learning from Retrieval: Towards Zero-shot Semantic ParsingAuthor 3 of 9ACL 2023
  30. Does the Correctness of Factual Knowledge Matter for Factual Knowledge-Enhanced Pre-trained Language Models?Author 3 of 5EMNLP 2023

Showing the 30 most recent indexed papers.

Dusk over the sea between two cliffs drawn in fine vertical lines