English
Related papers

Related papers: Neuro-Symbolic Proof Generation for Scaling System…

200 papers

Formal methods (FM) are reliable but costly to apply, often requiring years of expert effort in industrial-scale projects such as seL4, especially for theorem proving. Recent advances in large language models (LLMs) have made automated…

Cryptography and Security · Computer Science 2026-02-10 Jianyu Zhang , Fuyuan Zhang , Jiayi Lu , Jilin Hu , Xiaoyi Yin , Long Zhang , Feng Yang , Yongwang Zhao

Chain-of-Thought (CoT) prompting has become the de facto method to elicit reasoning capabilities from large language models (LLMs). However, to mitigate hallucinations in CoT that are notoriously difficult to detect, current methods such as…

Computation and Language · Computer Science 2025-06-06 Chengwu Liu , Ye Yuan , Yichun Yin , Yan Xu , Xin Xu , Zaoyu Chen , Yasheng Wang , Lifeng Shang , Qun Liu , Ming Zhang

Large Language Models (LLMs) often struggle with complex mathematical reasoning, where prose-based generation leads to unverified and arithmetically unsound solutions. Current prompting strategies like Chain of Thought still operate within…

Computation and Language · Computer Science 2026-01-27 Sina Bagheri Nezhad , Yao Li , Ameeta Agrawal

Neural Theorem Proving (NTP) employs LLMs to automate formal proofs in proof assistants. While LLMs have achieved relatively remarkable success in informal reasoning tasks using natural languages, the transition to mechanized formal theorem…

Programming Languages · Computer Science 2025-12-24 Qiyuan Xu , Renxi Wang , Peixin Wang , Haonan Li , Conrad Watt

Synthetic verification techniques such as generating test cases and reward modelling are common ways to enhance the coding capabilities of large language models (LLM) beyond predefined tests. Additionally, code verification has recently…

Artificial Intelligence · Computer Science 2025-07-31 Aleksander Ficek , Somshubra Majumdar , Vahid Noroozi , Boris Ginsburg

The rise of automated code generation tools, such as large language models (LLMs), has introduced new challenges in ensuring the correctness and efficiency of scientific software, particularly in complex kernels, where numerical stability,…

Programming Languages · Computer Science 2025-01-17 Naifeng Zhang , Sanil Rao , Mike Franusich , Franz Franchetti

Formal theorem proving, a field at the intersection of mathematics and computer science, has seen renewed interest with advancements in large language models (LLMs). This paper introduces SubgoalXL, a novel approach that synergizes…

Machine Learning · Computer Science 2024-08-22 Xueliang Zhao , Lin Zheng , Haige Bo , Changran Hu , Urmish Thakker , Lingpeng Kong

Large Language Model (LLM) reasoning for complex tasks inherently involves a trade-off between solution accuracy and computational efficiency. The subsequent step of verification, while intended to improve performance, further complicates…

Artificial Intelligence · Computer Science 2025-05-20 Jianyuan Zhong , Zeju Li , Zhijian Xu , Xiangyu Wen , Kezhi Li , Qiang Xu

Neuro-symbolic NLP methods aim to leverage the complementary strengths of large language models and formal logical solvers. However, current approaches are mostly static in nature, i.e., the integration of a target solver is predetermined…

Computation and Language · Computer Science 2025-10-09 Lei Xu , Pierre Beckmann , Marco Valentino , André Freitas

Ensuring correctness is a pivotal aspect of software engineering. Among the various strategies available, software verification offers a definitive assurance of correctness. Nevertheless, writing verification proofs is resource-intensive…

Software Engineering · Computer Science 2024-06-06 Lichen Zhang , Shuai Lu , Nan Duan

Interactive theorem provers such as Coq are powerful tools to formally guarantee the correctness of software. However, using these tools requires significant manual effort and expertise. While Large Language Models (LLMs) have shown promise…

Software Engineering · Computer Science 2024-09-24 Minghai Lu , Benjamin Delaware , Tianyi Zhang

Interactive theorem provers (ITPs) are powerful tools for the formal verification of mathematical proofs down to the axiom level. However, their lack of a natural language interface remains a significant limitation. Recent advancements in…

Logic in Computer Science · Computer Science 2025-07-01 Xiaolin Hu , Qinghua Zhou , Bogdan Grechuk , Ivan Y. Tyukin

Recent advances in large language models (LLMs) have enabled the automatic generation of executable code for task planning and control in embodied agents such as robots, demonstrating the potential of LLM-based embodied intelligence.…

Artificial Intelligence · Computer Science 2025-10-27 Sanghyun Ahn , Wonje Choi , Junyong Lee , Jinwoo Park , Honguk Woo

Large Language Models perform well at natural language interpretation and reasoning, but their inherent stochasticity limits their adoption in regulated industries like finance and healthcare that operate under strict policies. To address…

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 high-quality mathematical data. To explore this, we developed…

Artificial Intelligence · Computer Science 2024-12-09 Zenan Li , Zhi Zhou , Yuan Yao , Yu-Feng Li , Chun Cao , Fan Yang , Xian Zhang , Xiaoxing Ma

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 tactics is vast and complex, while the available training data…

Artificial Intelligence · Computer Science 2025-02-28 Zenan Li , Zhaoyu Li , Wen Tang , Xian Zhang , Yuan Yao , Xujie Si , Fan Yang , Kaiyu Yang , Xiaoxing Ma

Large Language Models (LLMs) have shown remarkable reasoning performance but struggle with multi-step deductive reasoning involving a series of rule application steps, especially when rules are presented non-sequentially. Our preliminary…

Computation and Language · Computer Science 2024-08-27 Siyuan Wang , Zhongyu Wei , Yejin Choi , Xiang Ren

Large Language Models (LLMs) demonstrate impressive mathematical reasoning abilities, but their solutions frequently contain errors that cannot be automatically checked. Formal theorem proving systems such as Lean 4 offer automated…

Artificial Intelligence · Computer Science 2026-03-18 Sumanth Varambally , Thomas Voice , Yanchao Sun , Zhifeng Chen , Rose Yu , Ke Ye

Multi-step reasoning improves the capabilities of large language models (LLMs) but increases the risk of errors propagating through intermediate steps. Process reward models (PRMs) mitigate this by scoring each step individually, enabling…

Computation and Language · Computer Science 2026-03-19 Corentin Royer , Debarun Bhattacharjya , Gaetano Rossiello , Andrea Giovannini , Mennatallah El-Assady

Recent work on reinforcement learning with verifiable rewards (RLVR) has shown that large language models (LLMs) can be substantially improved using outcome-level verification signals, such as unit tests for code or exact-match checks for…

Computation and Language · Computer Science 2026-01-27 Massimiliano Pronesti , Anya Belz , Yufang Hou