5 papers
Word Salad Chopper: Reasoning Models Waste A Ton Of Decoding Budget On Useless Repetitions, Self-Knowingly
Wenya Xie, Shaochen, Zhong +4
Large Reasoning Models (LRMs) are often bottlenecked by the high cost of output tokens. We show that a significant portion of these tokens are useless self-repetitions - what we ca…
Understanding and Mitigating Numerical Sources of Nondeterminism in LLM Inference
Jiayi Yuan, Hao Li, Xinheng Ding +7
Large Language Models (LLMs) are now integral across various domains and have demonstrated impressive performance. Progress, however, rests on the premise that benchmark scores are…
How Memory Management Impacts LLM Agents: An Empirical Study of Experience-Following Behavior
Zidi Xiong, Yuping Lin, Wenya Xie +5
Memory is a critical component in large language model (LLM)-based agents, enabling them to store and retrieve past executions to improve task performance over time. In this paper,…
Automating Expert-Level Medical Reasoning Evaluation of Large Language Models
Shuang Zhou, Wenya Xie, Jiaxi Li +16
As large language models (LLMs) become increasingly integrated into clinical decision-making, ensuring transparent and trustworthy reasoning is essential. However, existing evaluat…
Knowledge Boundary of Large Language Models: A Survey
Moxin Li, Yong Zhao, Wenxuan Zhang +5
Although large language models (LLMs) store vast amount of knowledge in their parameters, they still have limitations in the memorization and utilization of certain knowledge, lead…