English
Related papers

Related papers: ATLAS: Autoformalizing Theorems through Lifting, A…

200 papers

Interactive theorem provers (ITPs) require manual formalization, which is labor-intensive and demands expert knowledge. While automated formalization offers a potential solution, it faces two major challenges: model hallucination (e.g.,…

Artificial Intelligence · Computer Science 2026-03-24 Wangyue Lu , Lun Du , Sirui Li , Ke Weng , Haozhe Sun , Hengyu Liu , Minghe Yu , Tiancheng Zhang , Ge Yu

Current autoformalization benchmarks are largely focused on olympiad or undergraduate mathematics, while graduate and research-level mathematics remains underexplored. In this paper, we introduce MathAtlas, the first large-scale…

Verifiable formal languages like Lean have profoundly impacted mathematical reasoning, particularly through the use of large language models (LLMs) for automated reasoning. A significant challenge in training LLMs for these formal languages…

Computation and Language · Computer Science 2025-02-28 Guoxiong Gao , Yutong Wang , Jiedong Jiang , Qi Gao , Zihan Qin , Tianyi Xu , Bin Dong

The rapid advancement of Large Language Models (LLMs) has led to performance saturation on many established benchmarks, questioning their ability to distinguish frontier models. Concurrently, existing high-difficulty benchmarks often suffer…

While extensive research has explored the use of large language models (LLMs) for table-based reasoning, most approaches struggle with scalability when applied to large tables. To maintain the superior comprehension abilities of LLMs in…

Computation and Language · Computer Science 2024-07-04 Han Zhang , Yuheng Ma , Hanfang Yang

While large language models (LLMs) have shown progress in mathematical reasoning, they still face challenges in formalizing theorems that arise from instantiating abstract structures in concrete settings. With the goal of auto-formalizing…

Artificial Intelligence · Computer Science 2025-11-14 Chenyi Li , Wanli Ma , Zichen Wang , Zaiwen Wen

Enhancing the mathematical reasoning of large language models (LLMs) demands high-quality training data, yet conventional methods face critical challenges in scalability, cost, and data reliability. To address these limitations, we propose…

Computation and Language · Computer Science 2025-08-27 Sirui Chen , Changxin Tian , Binbin Hu , Kunlong Chen , Ziqi Liu , Zhiqiang Zhang , Jun Zhou

Autoformalization, the conversion of natural language mathematics into formal languages, offers significant potential for advancing mathematical reasoning. However, existing efforts are limited to formal languages with substantial online…

The integration of large language models (LLMs) with external tools has significantly expanded the capabilities of AI agents. However, as the diversity of both LLMs and tools increases, selecting the optimal model-tool combination becomes a…

Computation and Language · Computer Science 2026-01-08 Jinyang Wu , Guocheng Zhai , Ruihan Jin , Jiahao Yuan , Yuhao Shen , Shuai Zhang , Zhengqi Wen , Jianhua Tao

Modern large language models (LLMs) show promising progress in formalizing informal mathematics into machine-verifiable theorems. However, these methods still face bottlenecks due to the limited quantity and quality of multilingual parallel…

Computation and Language · Computer Science 2025-07-14 Jiyao Zhang , Chengli Zhong , Hui Xu , Qige Li , Yi Zhou

Recent work on activation and latent steering has demonstrated that modifying internal representations can effectively guide large language models (LLMs) toward improved reasoning and efficiency without additional training. However, most…

Machine Learning · Computer Science 2026-01-07 Tuc Nguyen , Thai Le

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…

Artificial Intelligence · Computer Science 2025-11-05 Azim Ospanov , Farzan Farnia , Roozbeh Yousefzadeh

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…

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…

Computation and Language · Computer Science 2024-10-15 Jianqiao Lu , Yingjia Wan , Yinya Huang , Jing Xiong , Zhengying Liu , Zhijiang Guo

Automated speaking assessment (ASA) on opinion expressions is often hampered by the scarcity of labeled recordings, which restricts prompt diversity and undermines scoring reliability. To address this challenge, we propose a novel training…

Computation and Language · Computer Science 2025-09-12 Chung-Chun Wang , Jhen-Ke Lin , Hao-Chien Lu , Hong-Yun Lin , Berlin Chen

Autoformalization plays a crucial role in formal mathematical reasoning by enabling the automatic translation of natural language statements into formal languages. While recent advances using large language models (LLMs) have shown…

Computation and Language · Computer Science 2025-06-13 Lan Zhang , Marco Valentino , Andre Freitas

Existing approaches to constructing training data for Natural Language Inference (NLI) tasks, such as for semi-structured table reasoning, are either via crowdsourcing or fully automatic methods. However, the former is expensive and…

Computation and Language · Computer Science 2022-10-25 Dibyakanti Kumar , Vivek Gupta , Soumya Sharma , Shuo Zhang

Data augmentation has been widely used to improve deep neural networks in many research fields, such as computer vision. However, less work has been done in the context of text, partially due to its discrete nature and the complexity of…

Computation and Language · Computer Science 2021-01-12 Ping Yu , Ruiyi Zhang , Yang Zhao , Yizhe Zhang , Chunyuan Li , Changyou Chen

Autoformalization serves a crucial role in connecting natural language and formal reasoning. This paper presents MASA, a novel framework for building multi-agent systems for autoformalization driven by Large Language Models (LLMs). MASA…

Computation and Language · Computer Science 2025-10-13 Lan Zhang , Marco Valentino , André Freitas

Combining large language models with logical reasoning enhances their capacity to address problems in a robust and reliable manner. Nevertheless, the intricate nature of logical reasoning poses challenges when gathering reliable data from…