中文
相关论文

相关论文: Draft, Sketch, and Prove: Guiding Formal Theorem P…

200 篇论文

Recent advancements, such as DeepSeek-Prover-V2-671B and Kimina-Prover-Preview-72B, demonstrate a prevailing trend in leveraging reinforcement learning (RL)-based large-scale training for automated theorem proving. Surprisingly, we discover…

人工智能 · 计算机科学 2025-06-16 Chenrui Cao , Liangcheng Song , Zenan Li , Xinyi Le , Xian Zhang , Hui Xue , Fan Yang

Reasoning methods such as chain-of-thought prompting and self-consistency have shown immense potential to improve the accuracy of large language models across various reasoning tasks. However such methods involve generation of lengthy…

计算与语言 · 计算机科学 2025-10-30 Disha Sheshanarayana , Tanishka Magar

Artificial intelligence assisted mathematical proof has become a highly focused area nowadays. One key problem in this field is to generate formal mathematical proofs from natural language proofs. Due to historical reasons, the formal proof…

编程语言 · 计算机科学 2024-05-14 Lihan Xie , Zhicheng Hui , Qinxiang Cao

Although most of the automated theorem-proving approaches depend on formal proof systems, informal theorem proving can align better with large language models' (LLMs) strength in natural language processing. In this work, we identify a…

人工智能 · 计算机科学 2026-04-20 Yunhe Li , Hao Shi , Bowen Deng , Wei Wang , Mengzhe Ruan , Hanxu Hou , Zhongxiang Dai , Siyang Gao , Chao Wang , Shuang Qiu , Linqi Song

The advent of large pre-trained language models has made it possible to make high-quality predictions on how to add or change a sentence in a document. However, the high branching factor inherent to text generation impedes the ability of…

计算与语言 · 计算机科学 2021-06-15 Zeqiu Wu , Michel Galley , Chris Brockett , Yizhe Zhang , Bill Dolan

Auto-formalization (AF) translates natural-language reasoning problems into solver-executable programs, enabling symbolic solvers to perform sound logical deduction. In practice, however, AF pipelines are currently brittle: programs may…

Automating the formalization of mathematical statements for theorem proving remains a major challenge for Large Language Models (LLMs). LLMs struggle to identify and utilize the prerequisite mathematical knowledge and its corresponding…

人工智能 · 计算机科学 2026-04-08 Meiru Zhang , Philipp Borchert , Milan Gritta , Gerasimos Lampouras

Formal verification using interactive theorem provers ensures high-quality software. However, writing proof scripts for interactive theorem provers is labor-intensive and requires deep expertise. Recent studies have leveraged deep learning…

计算机科学中的逻辑 · 计算机科学 2026-04-28 Manqing Zhang , Yunwei Dong , Lingru Zhou , Bingxu Xiao , Yepang Liu

Many recent prompting strategies for large language models (LLMs) query the model multiple times sequentially -- first to produce intermediate results and then the final answer. However, using these methods, both decoder and model are…

计算与语言 · 计算机科学 2023-11-10 Luca Beurer-Kellner , Mark Niklas Müller , Marc Fischer , Martin Vechev

Mathematics formalisation is the task of writing mathematics (i.e., definitions, theorem statements, proofs) in natural language, as found in books and papers, into a formal language that can then be checked for correctness by a program. It…

计算与语言 · 计算机科学 2022-11-15 Ayush Agrawal , Siddhartha Gadgil , Navin Goyal , Ashvni Narayanan , Anand Tadipatri

The automated generation of exercises may substantially reduce the time educators devote to manual exercise design. A major obstacle to the integration of such automation into teaching practice, however, lies in the ability to control the…

计算机科学中的逻辑 · 计算机科学 2026-03-10 João Mendes , João Marcos , Patrick Terrematte

Real-life conjectures do not come with instructions saying whether they they should be proven or, instead, refuted. Yet, as we now know, in either case the final argument produced had better be not just convincing but actually verifiable in…

计算机与社会 · 计算机科学 2015-07-21 João Marcos

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…

计算机科学中的逻辑 · 计算机科学 2025-07-01 Xiaolin Hu , Qinghua Zhou , Bogdan Grechuk , Ivan Y. Tyukin

Autoformalization has emerged as a term referring to the automation of formalization - specifically, the formalization of mathematics using interactive theorem provers (proof assistants). Its rapid development has been driven by progress in…

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

Automated theorem provers and formal proof assistants are general reasoning systems that are in theory capable of proving arbitrarily hard theorems, thus solving arbitrary problems reducible to mathematics and logical reasoning. In…

人工智能 · 计算机科学 2025-06-23 Lasse Blaauwbroek , David Cerna , Thibault Gauthier , Jan Jakubův , Cezary Kaliszyk , Martin Suda , Josef Urban

Large language models (LLMs) excel at natural language reasoning but remain unreliable on tasks requiring strict rule adherence, determinism, and auditability. Logic Sketch Prompting (LSP) is a lightweight prompting framework that…

人工智能 · 计算机科学 2025-12-30 Satvik Tripathi

Recent advances in automated theorem proving use Large Language Models (LLMs) to translate informal mathematical statements into formal proofs. However, informal cues are often ambiguous or lack strict logical structure, making it hard for…

机器学习 · 计算机科学 2025-10-14 Shashank Kirtania , Arun Iyer

This paper proposes a natural language translation method for machine-verifiable formal proofs that leverages the informalization (verbalization of formal language proof steps) and summarization capabilities of LLMs. For evaluation, it was…

计算与语言 · 计算机科学 2025-09-15 Seiji Hattori , Takuya Matsuzaki , Makoto Fujiwara

Although automated reasoning with diagrams has been possible for some years, tools for diagrammatic reasoning are generally much less sophisticated than their sentential cousins. The tasks of exploring levels of automation and abstraction…

计算机科学中的逻辑 · 计算机科学 2017-01-26 Sven Linker , Jim Burton , Mateja Jamnik
‹ 上一页 1 2 3 10 下一页 ›