English
Related papers

Related papers: LeanTutor: Towards a Verified AI Mathematical Proo…

200 papers

This paper investigates the logical reasoning capabilities of large language models (LLMs). For a precisely defined yet tractable formulation, we choose the conceptually simple but technically complex task of constructing proofs in Boolean…

Machine Learning · Computer Science 2025-04-30 Yuan Xia , Akanksha Atrey , Fadoua Khmaissia , Kedar S. Namjoshi

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…

Artificial Intelligence · Computer Science 2025-10-02 Balaji Rao , William Eiers , Carlo Lipizzi

Large language models (LLMs) have been used to generate formal proofs of mathematical theorems in proofs assistants such as Lean. However, we often want to optimize a formal proof with respect to various criteria, depending on its…

Artificial Intelligence · Computer Science 2026-05-22 Riyaz Ahuja , Jeremy Avigad , Prasad Tetali , Sean Welleck

The large language models (LLMs) might produce a persuasive argument within mathematical and logical fields, although such argument often includes some minor missteps, including the entire omission of side conditions, invalid inference…

Artificial Intelligence · Computer Science 2026-04-09 Kranthi Kommuru , Kunal Khanvilkar , Gaurav Parekh

Formal theorem proving with TLA+ provides rigorous guarantees for system specifications, but constructing proofs requires substantial expertise and effort. While large language models have shown promise in automating proofs for tactic-based…

Logic in Computer Science · Computer Science 2026-03-03 Yuhao Zhou , Stavros Tripakis

AI-driven autoformalization of mathematics is advancing rapidly. However, the type checker of a proof assistant guarantees only the logical correctness of proofs; it does not verify whether propositions and definitions faithfully capture…

Human-Computer Interaction · Computer Science 2026-04-21 Banri Yanahama , Akiyoshi Sannai

Formal mathematical reasoning remains a critical challenge for artificial intelligence, hindered by limitations of existing benchmarks in scope and scale. To address this, we present FormalMATH, a large-scale Lean4 benchmark comprising…

Proving mathematical theorems using computer-verifiable formal languages like Lean significantly impacts mathematical reasoning. One approach to formal theorem proving involves generating complete proofs using Large Language Models (LLMs)…

Formal Languages and Automata Theory · Computer Science 2024-10-07 Ruida Wang , Jipeng Zhang , Yizhen Jia , Rui Pan , Shizhe Diao , Renjie Pi , Tong Zhang

Large language models (LLMs) are increasingly embedded in AI-based tutoring systems. Can they faithfully model novice reasoning and metacognitive judgments? Existing evaluations emphasize problem-solving accuracy, overlooking the fragmented…

Computation and Language · Computer Science 2026-05-12 Conrad Borchers , Jill-Jênn Vie , Roger Azevedo

Intelligent tutoring systems have long enabled automated immediate feedback on student work when it is presented in a tightly structured format and when problems are very constrained, but reliably assessing free-form mathematical reasoning…

Computers and Society · Computer Science 2026-01-08 Aron Gohr , Marie-Amelie Lawn , Kevin Gao , Inigo Serjeant , Stephen Heslip

As artificial intelligence (AI) gains greater adoption in a wide variety of applications, it has immense potential to contribute to mathematical discovery, by guiding conjecture generation, constructing counterexamples, assisting in…

Artificial Intelligence · Computer Science 2023-10-27 Hassen Saidi , Susmit Jha , Tuhin Sahai

Large language models (LLMs) have significantly advanced formal theorem proving, yet the scarcity of high-quality training data constrains their capabilities in complex mathematical domains. Combinatorics, a cornerstone of mathematics,…

Artificial Intelligence · Computer Science 2025-02-26 Beibei Xiong , Hangyu Lv , Haojia Shan , Jianlin Wang , Zhengfeng Yang , Lihong Zhi

The combination of verifiable languages and LLMs has significantly influenced both the mathematical and computer science communities because it provides a rigorous foundation for theorem proving. Recent advancements in the field provide…

Artificial Intelligence · Computer Science 2026-01-23 Hanning Zhang , Ruida Wang , Rui Pan , Wenyuan Wang , Bingxu Meng , Tong Zhang

Automated theorem proving is essential for the formal verification of safety-critical systems. As the corpus of formal proofs grows, a natural paradigm is to learn from existing proofs. However, current learning-based approaches…

Software Engineering · Computer Science 2026-05-12 Jian Fang , Yixun Yao , Yingfei Xiong

Mathematical reasoning is a hallmark of human intelligence, and whether large language models (LLMs) can meaningfully perform it remains a central question in artificial intelligence and cognitive science. As LLMs are increasingly…

Computation and Language · Computer Science 2026-04-03 Linyang He , Qiyao Yu , Hanze Dong , Baohao Liao , Xinxing Xu , Micah Goldblum , Jiang Bian , Nima Mesgarani

As automated reasoning systems advance rapidly, there is a growing need for research-level formal mathematical problems to accurately evaluate their capabilities. To address this, we present Formal Conjectures, an evolving benchmark of…

Large language models (LLM) are perceived to offer promising potentials for automating security tasks, such as those found in security operation centers (SOCs). As a first step towards evaluating this perceived potential, we investigate the…

Cryptography and Security · Computer Science 2024-02-01 Kumar Shashwat , Francis Hahn , Xinming Ou , Dmitry Goldgof , Lawrence Hall , Jay Ligatti , S. Raj Rajgopalan , Armin Ziaie Tabari

Large language models have recently made significant progress to generate rigorous mathematical proofs. In contrast, utilizing LLMs for theorem proving in formal languages (such as Lean) remains challenging and computationally expensive,…

This paper presents our system for Track 1: Mistake Identification in the BEA 2025 Shared Task on Pedagogical Ability Assessment of AI-powered Tutors. The task involves evaluating whether a tutor's response correctly identifies a mistake in…

Computation and Language · Computer Science 2025-06-13 Numaan Naeem , Sarfraz Ahmad , Momina Ahsan , Hasan Iqbal

A fundamental challenge in formal theorem proving by LLMs is the lack of high-quality training data. Although reinforcement learning or expert iteration partially mitigates this issue by alternating between LLM generating proofs and…

Machine Learning · Computer Science 2025-03-24 Kefan Dong , Tengyu Ma