PPaperPicks

Wei Hu

Nanjing University, State Key Laboratory for Novel Software Technology, China

21 papers at tracked venues · 14 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. Answering the Unanswerable Is to Err Knowingly: Analyzing and Mitigating Abstention Failures in Large Reasoning Models
  2. Bootstrapping Code Translation with Weighted Multilanguage Exploration
  3. Do We Truly Need So Many Samples? Multi-LLM Repeated Sampling Efficiently Scales Test-Time Compute
  4. ProtSAE: Disentangling and Interpreting Protein Language Models via Semantically-Guided Sparse Autoencoders
  5. Are LLMs Really Knowledgeable for Knowledge Graph Completion?
  6. Avoiding Knowledge Edit Skipping in Multi-hop Question Answering with Guided Decomposition
  7. Controllable Protein Sequence Generation with LLM Preference Optimization
  8. Knowledge Graph-Guided Retrieval Augmented Generation
  9. Mitigating Lost-in-Retrieval Problems in Retrieval Augmented Multi-Hop Question Answering
  10. Parameter-Efficient Federated Knowledge Graph Embedding Learning and Unlearning
  11. WoW: A Window-to-Window Incremental Index for Range-Filtering Approximate Nearest Neighbor Search
  12. A Blockchain System for Clustered Federated Learning with Peer-to-Peer Knowledge Transfer
  13. A Prompt-Based Knowledge Graph Foundation Model for Universal In-Context Reasoning
  14. Dataflow-Guided Retrieval Augmentation for Repository-Level Code Completion
  15. Expanding the Scope: Inductive Knowledge Graph Reasoning with Multi-starting Progressive Propagation
  16. Finetuning Generative Large Language Models with Discrimination Instructions for Knowledge Graph Completion
  17. Generating Explanations to Understand and Repair Embedding-Based Entity Alignment
  18. KnowLA: Enhancing Parameter-efficient Finetuning with Knowledgeable Adaptation
  19. Knowledge Graph Error Detection with Contrastive Confidence Adaption
  20. Multi-Aspect Controllable Text Generation with Disentangled Counterfactual Augmentation
  21. Timeline-based Sentence Decomposition with In Context Learning for Temporal Fact Extraction