Profiles2024-2026
Baolong Bi
University of Chinese Academy of Sciences
15Papers
0Last author
19Unique co-authors
7First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers15
- Parameters vs. Context: Fine-Grained Control of Knowledge Reliance in Language ModelsAuthor 1 of 7ICLR 2026 · 47 citations
- Reward and Guidance through Rubrics: Promoting Exploration to Improve Multi-Domain ReasoningAuthor 1 of 9ICML 2026 · 19 citations
- HiddenGuard: Fine-Grained Safe Generation with Specialized Representation RouterAuthor 4 of 6ACL 2026 · 14 citations
- Gated Differentiable Working Memory for Long-Context Language ModelingAuthor 5 of 10ACL 2026 · 4 citations
- a1: Steep Test-time Scaling Law via Environment Augmented GenerationAuthor 4 of 8ACL Findings 2026
- Towards Fully Exploiting LLM Internal States to Enhance Knowledge Boundary PerceptionAuthor 5 of 6ACL 2025 · 22 citations
- Explainable and Efficient Editing for Large Language ModelsAuthor 4 of 6WWW 2025 · 8 citations
- Context-DPO: Aligning Language Models for Context-FaithfulnessAuthor 1 of 14ACL Findings 2025 · 2 citations
- Can Graph Descriptive Order Affect Solving Graph Problems with LLMs?Author 3 of 8ACL 2025
- Decoding by Contrasting Knowledge: Enhancing Large Language Model Confidence on Edited FactsAuthor 1 of 6ACL 2025
- Is Factuality Enhancement a Free Lunch For LLMs? Better Factuality Can Lead to Worse Context-FaithfulnessAuthor 1 of 8ICLR 2025
- Who is in the Spotlight: The Hidden Bias Undermining Multimodal Retrieval-Augmented GenerationAuthor 5 of 8EMNLP 2025
- SLANG: New Concept Comprehension of Large Language ModelsAuthor 4 of 5EMNLP 2024 · 7 citations
- LPNL: Scalable Link Prediction with Large Language ModelsAuthor 1 of 5ACL Findings 2024 · 6 citations
- Adaptive Token Biaser: Knowledge Editing via Biasing Key EntitiesAuthor 1 of 7EMNLP Findings 2024
