Lune

Profiles2024-2026ORCID 0000-0001-5123-4999

Keping Bi

University of Chinese Academy of Sciences

17Papers
4Last author
26Unique co-authors
0First author
0Solo

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

Recent papers17

  1. How Long Reasoning Chains Influence LLMs' Judgment of Answer FactualityAuthor 3 of 3ACL 2026 · 5 citations
  2. Compressing then Matching: An Efficient Pre-training Paradigm for Multimodal EmbeddingAuthor 3 of 10ACL 2026 · 3 citations
  3. Training Dense Retrievers with Multiple Positive PassagesAuthor 5 of 5KDD 2026 · 1 citation
  4. An Iterative Utility Judgment Framework Inspired by Philosophical Relevance via LLMsAuthor 2 of 4ACL Findings 2026
  5. Annotation-Efficient Honesty Alignment via Confidence Elicitation and CalibrationAuthor 2 of 7ICLR 2026
  6. Beyond Text-Only: Towards Multimodal Table Retrieval in Open-WorldAuthor 2 of 7ICLR 2026
  7. Reconstructing Content with Collaborative Attention for Universal Multimodal Representation LearningAuthor 9 of 9SIGIR 2026
  8. Towards Fully Exploiting LLM Internal States to Enhance Knowledge Boundary PerceptionAuthor 2 of 6ACL 2025 · 22 citations
  9. Evaluating Implicit Bias in Large Language Models by Attacking From a Psychometric PerspectiveAuthor 2 of 5ACL Findings 2025 · 2 citations
  10. Tailoring Table Retrieval from a Field-aware Hybrid Matching PerspectiveAuthor 2 of 4EMNLP 2025 · 1 citation
  11. Utility-Focused LLM Annotation for Retrieval and Retrieval-Augmented GenerationAuthor 3 of 8EMNLP 2025 · 1 citation
  12. CLIPure: Purification in Latent Space via CLIP for Adversarially Robust Zero-Shot ClassificationAuthor 2 of 5ICLR 2025
  13. Do LVLMs Know What They Know? A Systematic Study of Knowledge Boundary Perception in LVLMsAuthor 3 of 3EMNLP Findings 2025
  14. When Do LLMs Need Retrieval Augmentation? Mitigating LLMs' Overconfidence Helps Retrieval AugmentationAuthor 2 of 4ACL Findings 2024 · 13 citations
  15. CausalDiff: Causality-Inspired Disentanglement via Diffusion Model for Adversarial DefenseAuthor 2 of 6NeurIPS 2024 · 9 citations
  16. LINKAGE: Listwise Ranking among Varied-Quality References for Non-Factoid QA Evaluation via LLMsAuthor 2 of 5EMNLP Findings 2024 · 4 citations
  17. MORE: Multi-mOdal REtrieval Augmented Generative Commonsense ReasoningAuthor 2 of 4ACL Findings 2024 · 3 citations
Dusk over the sea between two cliffs drawn in fine vertical lines