4 papers
SourceBench: Can AI Answers Reference Quality Web Sources?
Hexi Jin, Stephen Liu, Yuheng Li +2
Large language models (LLMs) increasingly answer queries by citing web sources, but existing evaluations emphasize answer correctness rather than evidence quality. We introduce Sou…
ReBeCA: Unveiling Interpretable Behavior Hierarchy behind the Iterative Self-Reflection of Language Models with Causal Analysis
Tianqiang Yan, Sihan Shang, Yuheng Li +6
While self-reflection can enhance language model reliability, its underlying mechanisms remain opaque, with existing analyses often yielding correlation-based insights that fail to…
Enhancing Large Multimodal Models with Adaptive Sparsity and KV Cache Compression
Te Zhang, Yuheng Li, Junxiang Wang +1
Large multimodal models (LMMs) have advanced significantly by integrating visual encoders with extensive language models, enabling robust reasoning capabilities. However, compressi…
Can Reinforcement Learning Solve Asymmetric Combinatorial-Continuous Zero-Sum Games?
Yuheng Li, Panpan Wang, Haipeng Chen
There have been extensive studies on learning in zero-sum games, focusing on the analysis of the existence and algorithmic convergence of Nash equilibrium (NE). Existing studies ma…