collaborators

5 papers

cs.LG2025

A Theoretical Study on Bridging Internal Probability and Self-Consistency for LLM Reasoning

Zhi Zhou, Yuhao Tan, Zenan Li +4

Test-time scaling seeks to improve the reasoning performance of large language models (LLMs) by adding computational resources. A prevalent approach within the field is sampling-ba…

cs.CL2025

FormalML: A Benchmark for Evaluating Formal Subgoal Completion in Machine Learning Theory

Xiao-Wen Yang, Zihao Zhang, Jianuo Cao +7

Large language models (LLMs) have recently demonstrated remarkable progress in formal theorem proving. Yet their ability to serve as practical assistants for mathematicians, fillin…

cs.AI2025

Proving Olympiad Inequalities by Synergizing LLMs and Symbolic Reasoning

Zenan Li, Zhaoyu Li, Wen Tang +6

Large language models (LLMs) can prove mathematical theorems formally by generating proof steps (\textit{a.k.a.} tactics) within a proof system. However, the space of possible tact…

cs.LG2025

Bridging Internal Probability and Self-Consistency for Effective and Efficient LLM Reasoning

Zhi Zhou, Tan Yuhao, Zenan Li +4

Recent advancements in large language models (LLMs) have demonstrated remarkable reasoning capabilities. However, single-shot inference often yields unreliable results for complex…

cs.AI2024

Neuro-Symbolic Data Generation for Math Reasoning

Zenan Li, Zhi Zhou, Yuan Yao +5

A critical question about Large Language Models (LLMs) is whether their apparent deficiency in mathematical reasoning is inherent, or merely a result of insufficient exposure to hi…