10 papers
Planning to Hammer: Difficulty-Aware Decomposition for Automating Rocq Proofs
Ning Zhang, Nongyu Di, Zenan Li +2
As AI-generated code proliferates, formal verification, particularly through interactive theorem provers such as Rocq and Isabelle, becomes increasingly important for ensuring soft…
Uncertainty Quantification for LLM-based Code Generation
Senrong Xu, Yuhao Tan, Yanke Zhou +6
Prediction sets provide a theoretically grounded framework for quantifying uncertainty in machine learning models. Adapting them to structured generation tasks, in particular, larg…
Fair Conformal Classification via Learning Representation-Based Groups
Senrong Xu, Yanke Zhou, Yuhao Tan +5
Conformal prediction methods provide statistically rigorous marginal coverage guarantees for machine learning models, but such guarantees fail to account for algorithmic biases, th…
Learning to Bid with Unknown Private Values in Budget-Constrained First-Price Auctions
Zihao Hu, Yuxiao Wen, Yuan Yao +2
We study the operational problem of automated bidding in repeated first-price auctions under budget and return-on-spend (RoS) constraints. In this setting, an auto-bidder must tran…
Neuro-Symbolic Proof Generation for Scaling Systems Software Verification
Baoding He, Zenan Li, Wei Sun +4
Formal verification via interactive theorem proving is increasingly used to ensure the correctness of critical systems, yet constructing large proof scripts remains highly manual a…
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…
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…
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…
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…
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…