中文
相关论文

相关论文: Pseudo-Formalization for Automatic Proof Verificat…

200 篇论文

Formally verifying properties of software code has been a highly desirable task, especially with the emergence of LLM-generated code. In the same vein, they provide an interesting avenue for the exploration of formal verification and…

人工智能 · 计算机科学 2025-10-02 Balaji Rao , William Eiers , Carlo Lipizzi

Formal verification guarantees proof validity but not formalization faithfulness. For natural-language logical reasoning, where models construct axiom systems from scratch without library constraints, this gap between valid proofs and…

人工智能 · 计算机科学 2026-04-22 Kyuhee Kim , Auguste Poiroux , Antoine Bosselut

The challenge of formal proof generation has a rich history, but with modern techniques, we may finally be at the stage of making actual progress in real-life mathematical problems. This paper explores the integration of ChatGPT and basic…

计算机科学中的逻辑 · 计算机科学 2025-02-20 Sangjun Han , Taeil Hur , Youngmi Hur , Kathy Sangkyung Lee , Myungyoon Lee , Hyojae Lim

Large Language Models (LLMs) have demonstrated formidable capabilities in solving mathematical problems, yet they may still commit logical reasoning and computational errors during the problem-solving process. Thus, this paper proposes a…

人工智能 · 计算机科学 2025-05-28 Kuo Zhou , Lu Zhang

Autoformalization aims to translate natural-language mathematical statements into a formal language. While LLMs have accelerated progress in this area, existing methods still suffer from low accuracy. We identify two key abilities for…

计算与语言 · 计算机科学 2025-12-29 Yutong Wu , Di Huang , Ruosi Wan , Yue Peng , Shijie Shang , Chenrui Cao , Lei Qi , Rui Zhang , Zidong Du , Jie Yan , Xing Hu

Large language models (LLMs) have recently demonstrated remarkable progress in formal theorem proving. Yet their ability to serve as practical assistants for mathematicians, filling in missing steps within complex proofs, remains…

计算与语言 · 计算机科学 2025-10-06 Xiao-Wen Yang , Zihao Zhang , Jianuo Cao , Zhi Zhou , Zenan Li , Lan-Zhe Guo , Yuan Yao , Taolue Chen , Yu-Feng Li , Xiaoxing Ma

Large Language Models (LLMs) have recently emerged as powerful tools for autoformalization. Despite their impressive performance, these models can still struggle to produce grounded and verifiable formalizations. Recent work in text-to-SQL,…

计算与语言 · 计算机科学 2025-12-05 Hayden Moore , Asfahan Shah

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…

计算与语言 · 计算机科学 2025-06-06 Chengwu Liu , Ye Yuan , Yichun Yin , Yan Xu , Xin Xu , Zaoyu Chen , Yasheng Wang , Lifeng Shang , Qun Liu , Ming Zhang

Autoformalization aims to convert informal mathematical proofs into machine-verifiable formats, bridging the gap between natural and formal languages. However, ensuring semantic alignment between the informal and formalized statements…

计算与语言 · 计算机科学 2024-10-15 Jianqiao Lu , Yingjia Wan , Yinya Huang , Jing Xiong , Zhengying Liu , Zhijiang Guo

Autoformalization - automatically translating natural language mathematical texts into formal proof language such as Lean4 - can help accelerate AI-assisted mathematical research, be it via proof verification or proof search. I fine-tune…

计算与语言 · 计算机科学 2026-03-26 Arsen Shebzukhov

Formal verification is increasingly recognized as a critical foundation for building reliable software systems. However, the need for specialized expertise to write precise specifications, navigate complex proof obligations, and learn…

软件工程 · 计算机科学 2025-10-31 Changjie Wang , Mariano Scazzariello , Anoud Alshnakat , Roberto Guanciale , Dejan Kostić , Marco Chiesa

Translating human-written mathematical theorems and proofs from natural language (NL) into formal languages (FLs) like Lean 4 has long been a significant challenge for AI. Most state-of-the-art methods either focus on theorem-only NL-to-FL…

计算机科学中的逻辑 · 计算机科学 2026-03-31 Prithwish Jana , Kaan Kale , Ahmet Ege Tanriverdi , Cruise Song , Sriram Vishwanath , Vijay Ganesh

Using AI to write formal proofs for mathematical problems is a challenging task that has seen some advancements in recent years. Automated systems such as Lean can verify the correctness of proofs written in formal language, yet writing the…

机器学习 · 计算机科学 2025-03-04 Roozbeh Yousefzadeh , Xuenan Cao , Azim Ospanov

Theorem proving serves as a major testbed for evaluating complex reasoning abilities in large language models (LLMs). However, traditional automated theorem proving (ATP) approaches rely heavily on formal proof systems that poorly align…

In the digital age, ensuring the correctness, safety, and reliability of software through formal verification is paramount, particularly as software increasingly underpins critical infrastructure. Formal verification, split into theorem…

软件工程 · 计算机科学 2026-04-03 Zhiyong Chen , Jialun Cao , Jiarong Wu , Chang Xu , Shing-Chi Cheung

Recent frontier large language models (LLMs) have shown strong performance in identifying security vulnerabilities in large, mature open-source systems. As LLM-generated code becomes increasingly common, a natural goal is to prevent such…

软件工程 · 计算机科学 2026-05-13 Zhaorui Li , Chengyu Song

Current approaches for formal verification of algorithms face important limitations. For specification, they cannot express algorithms naturally and concisely, especially for algorithms with states and flexible control flow. For…

编程语言 · 计算机科学 2025-05-01 Chengxi Yang , Shushu Wu , Qinxiang Cao

Formal reasoning and automated theorem proving constitute a challenging subfield of machine learning, in which machines are tasked with proving mathematical theorems using formal languages like Lean. A formal verification system can check…

人工智能 · 计算机科学 2025-11-05 Azim Ospanov , Farzan Farnia , Roozbeh Yousefzadeh

Autoformalization, which translates natural language mathematics into machine-verifiable formal statements, is critical for using formal mathematical reasoning to solve math problems stated in natural language. While Large Language Models…

计算与语言 · 计算机科学 2026-02-11 Guoxin Chen , Jing Wu , Xinjie Chen , Wayne Xin Zhao , Ruihua Song , Chengxi Li , Kai Fan , Dayiheng Liu , Minpeng Liao

This paper considers the development of an AI-based provably-correct mathematical proof tutor. While Large Language Models (LLMs) allow seamless communication in natural language, they are error prone. Theorem provers such as Lean allow for…

机器学习 · 计算机科学 2026-03-05 Manooshree Patel , Rayna Bhattacharyya , Thomas Lu , Arnav Mehta , Niels Voss , Narges Norouzi , Gireeja Ranade