English
Related papers

Related papers: Learning to Prove Theorems via Interacting with Pr…

200 papers

Neural theorem proving has advanced rapidly in the past year, reaching IMO gold-medalist capabilities and producing formal proofs that span thousands of lines. Although such proofs are mechanically verified by formal systems like Lean,…

Machine Learning · Computer Science 2025-10-20 Alex Gu , Bartosz Piotrowski , Fabian Gloeckle , Kaiyu Yang , Aram H. Markosyan

When demonstrating a task, human tutors pedagogically modify their behavior by either "showing" the task rather than just "doing" it (exaggerating on relevant parts of the demonstration) or by giving demonstrations that best disambiguate…

Machine Learning · Computer Science 2023-09-28 Hugo Caselles-Dupré , Mohamed Chetouani , Olivier Sigaud

Machine reading is a fundamental task for testing the capability of natural language understanding, which is closely related to human cognition in many aspects. With the rising of deep learning techniques, algorithmic models rival human…

Computation and Language · Computer Science 2020-07-17 Jian Liu , Leyang Cui , Hanmeng Liu , Dandan Huang , Yile Wang , Yue Zhang

The motivation for this paper comes out of our experience with teaching natural deduction (ND) and with the way this formal system is implemented by the \textsc{Coq} proof assistant, namely by means of so-called tactics, which are…

Computers and Society · Computer Science 2015-07-15 Favio E. Miranda-Perea , P. Selene Linares-Arévalo , Atocha Aliseda

We propose a learning analytics-based methodology for assessing the collaborative writing of humans and generative artificial intelligence. Framed by the evidence-centered design, we used elements of knowledge-telling, knowledge…

Human-Computer Interaction · Computer Science 2024-01-18 Yixin Cheng , Kayley Lyons , Guanliang Chen , Dragan Gasevic , Zachari Swiecki

Theorem proving is fundamental to program verification, where the automated proof of Verification Conditions (VCs) remains a primary bottleneck. Real-world program verification frequently encounters hard VCs that existing Automated Theorem…

Artificial Intelligence · Computer Science 2026-01-29 Qiyuan Xu , Xiaokun Luan , Renxi Wang , Joshua Ong Jun Leang , Peixin Wang , Haonan Li , Wenda Li , Conrad Watt

We present the Sequent Calculus Trainer, a tool that supports students in learning how to correctly construct proofs in the sequent calculus for first-order logic with equality. It is a proof assistant fostering the understanding of all the…

Computers and Society · Computer Science 2015-07-15 Arno Ehle , Norbert Hundeshagen , Martin Lange

Domain of mathematical logic in computers is dominated by automated theorem provers (ATP) and interactive theorem provers (ITP). Both of these are hard to access by AI from the human-imitation approach: ATPs often use human-unfriendly…

Logic in Computer Science · Computer Science 2020-05-08 Miroslav Olšák

Recent advancements in large language models (LLMs) underscore the need for more comprehensive evaluation methods to accurately assess their reasoning capabilities. Existing benchmarks are often domain-specific and thus cannot fully capture…

Formally verifying system properties is one of the most effective ways of improving system quality, but its high manual effort requirements often render it prohibitively expensive. Tools that automate formal verification, by learning from…

Programming Languages · Computer Science 2023-08-10 Alex Sanchez-Stern , Emily First , Timothy Zhou , Zhanna Kaufman , Yuriy Brun , Talia Ringer

Analytical reasoning is an essential and challenging task that requires a system to analyze a scenario involving a set of particular circumstances and perform reasoning over it to make conclusions. In this paper, we study the challenge of…

Computation and Language · Computer Science 2021-04-16 Wanjun Zhong , Siyuan Wang , Duyu Tang , Zenan Xu , Daya Guo , Jiahai Wang , Jian Yin , Ming Zhou , Nan Duan

Evaluating the mathematical capability of Large Language Models (LLMs) is a critical yet challenging frontier. Existing benchmarks fall short, particularly for proof-centric problems, as manual creation is unscalable and costly, leaving the…

Computation and Language · Computer Science 2025-08-06 Yebo Peng , Zixiang Liu , Yaoming Li , Zhizhuo Yang , Xinye Xu , Bowen Ye , Weijun Yuan , Zihan Wang , Tong Yang

We present an environment, benchmark, and deep learning driven automated theorem prover for higher-order logic. Higher-order interactive theorem provers enable the formalization of arbitrary mathematical theories and thereby present an…

Logic in Computer Science · Computer Science 2019-11-05 Kshitij Bansal , Sarah M. Loos , Markus N. Rabe , Christian Szegedy , Stewart Wilcox

Understanding the world and explaining it with scientific theories is a central aspiration of artificial intelligence research. Proposing theories, designing experiments to test them, and then revising them based on data are fundamental to…

Machine Learning · Computer Science 2025-10-16 Kanishk Gandhi , Michael Y. Li , Lyle Goodyear , Agam Bhatia , Louise Li , Aditi Bhaskar , Mohammed Zaman , Noah D. Goodman

Automatic theorem proving with deep learning methods has attracted attentions recently. In this paper, we construct an automatic proof system for trigonometric identities. We define the normalized form of trigonometric identities, design a…

Machine Learning · Computer Science 2022-07-15 Zhou Liu , Yujun Li , Zhengying Liu , Lin Li , Zhenguo Li

This paper presents two concrete applications of Artificial Intelligence to algorithmic and analytic number theory. Recent benchmarks of large language models have mainly focused on general mathematics problems and the currently infeasible…

Number Theory · Mathematics 2026-05-12 Ali Saraeb

In learning-assisted theorem proving, one of the most critical challenges is to generalize to theorems unlike those seen at training time. In this paper, we introduce INT, an INequality Theorem proving benchmark, specifically designed to…

Artificial Intelligence · Computer Science 2021-04-06 Yuhuai Wu , Albert Qiaochu Jiang , Jimmy Ba , Roger Grosse

Large Language Models (LLMs) are now widely used in astrophysics, but do they actually make our lives easier, or do they merely invent new physics with enough confidence to hide a minus sign? In a specialized field where checking fluent…

Instrumentation and Methods for Astrophysics · Physics 2026-04-01 Chun Huang

For performance and verification in machine learning, new methods have recently been proposed that optimise learning systems to satisfy formally expressed logical properties. Among these methods, differentiable logics (DLs) are used to…

Logic in Computer Science · Computer Science 2024-07-08 Reynald Affeldt , Alessandro Bruni , Ekaterina Komendantskaya , Natalia Ślusarz , Kathrin Stark

Automated theorem proving (ATP) has become an appealing domain for exploring the reasoning ability of the recent successful generative language models. However, current ATP benchmarks mainly focus on symbolic inference, but rarely involve…

‹ Prev 1 8 9 10 Next ›