English
Related papers

Related papers: CriticLean: Critic-Guided Reinforcement Learning f…

200 papers

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…

Computation and Language · Computer Science 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

Critique ability, i.e., the capability of Large Language Models (LLMs) to identify and rectify flaws in responses, is crucial for their applications in self-improvement and scalable oversight. While numerous studies have been proposed to…

Computation and Language · Computer Science 2024-10-22 Tian Lan , Wenwei Zhang , Chen Xu , Heyan Huang , Dahua Lin , Kai Chen , Xian-ling Mao

Faithfully personalizing large language models (LLMs) to align with individual user preferences is a critical but challenging task. While supervised fine-tuning (SFT) quickly reaches a performance plateau, standard reinforcement learning…

Computation and Language · Computer Science 2025-10-22 Chenghao Zhu , Meiling Tao , Tiannan Wang , Dongyi Ding , Yuchen Eleanor Jiang , Wangchunshu Zhou

Instruction-based image editing exhibits heterogeneous difficulty not only across cases but also across regions of an image, motivating refinement approaches that allocate correction to where the model struggles. Existing refinement signals…

Computer Vision and Pattern Recognition · Computer Science 2026-05-14 Weitai Kang , Xiaohang Zhan , Yizhou Wang , Mang Tik Chiu , Jason Kuen , Kangning Liu , Yan Yan

Education in the practical applications of logic and proving such as the formal specification and verification of computer programs is substantially hampered by the fact that most time and effort that is invested in proving is actually…

Logic in Computer Science · Computer Science 2018-03-06 Wolfgang Schreiner , Alexander Brunhuemer , Christoph Fürst

Instruction-following is a fundamental ability of Large Language Models (LLMs), requiring their generated outputs to follow multiple constraints imposed in input instructions. Numerous studies have attempted to enhance this ability through…

Computation and Language · Computer Science 2026-04-17 Bosi Wen , Yilin Niu , Cunxiang Wang , Pei Ke , Xiaoying Ling , Ying Zhang , Aohan Zeng , Hongning Wang , Minlie Huang

The research in AI-based formal mathematical reasoning has shown an unstoppable growth trend. These studies have excelled in mathematical competitions like IMO and have made significant progress. This paper focuses on formal verification,…

Artificial Intelligence · Computer Science 2025-06-10 Jialun Cao , Yaojie Lu , Meiziniu Li , Haoyang Ma , Haokun Li , Mengda He , Cheng Wen , Le Sun , Hongyu Zhang , Shengchao Qin , Shing-Chi Cheung , Cong Tian

Large language models are increasingly used to generate code from natural language, but ensuring correctness remains challenging. Formal verification offers a principled way to obtain such guarantees by proving that a program satisfies a…

Machine Learning · Computer Science 2026-04-14 Zhe Ye , Aidan Z. H. Yang , Huangyuan Su , Zhenyu Liao , Samuel Tenka , Zhizhen Qin , Udaya Ghai , Dawn Song , Soonho Kong

We perform a thorough analysis of the formal and informal statements in the miniF2F benchmark from the perspective of an AI system that is tasked to participate in a math Olympiad consisting of the problems in miniF2F. In such setting, the…

Artificial Intelligence · Computer Science 2025-11-06 Azim Ospanov , Farzan Farnia , Roozbeh Yousefzadeh

Recent advances in large language models (LLMs) have shown promise in formal theorem proving, yet evaluating semantic correctness remains challenging. Existing evaluations rely on indirect proxies such as lexical overlap with…

Computation and Language · Computer Science 2026-04-29 Jongyoon Kim , Hojae Han , Seung-won Hwang

This paper takes a first step towards a critical thinking curriculum for neural auto-regressive language models. We introduce a synthetic corpus of deductively valid arguments, and generate artificial argumentative texts to train and…

Computation and Language · Computer Science 2020-12-18 Gregor Betz , Christian Voigt , Kyle Richardson

Reactive synthesis, the problem of automatically constructing a hardware circuit from a logical specification, is a long-standing challenge in formal verification. It is elusive for two reasons: It is algorithmically hard, and writing…

Recently, large language models have presented promising results in aiding formal mathematical reasoning. However, their performance is restricted due to the scarcity of formal theorem-proving data, which requires additional effort to be…

Artificial Intelligence · Computer Science 2024-07-25 Zijian Wu , Jiayu Wang , Dahua Lin , Kai Chen

Reinforcement learning from human feedback (RLHF) is fundamentally limited by the capacity of humans to correctly evaluate model output. To improve human evaluation ability and overcome that limitation this work trains "critic" models that…

Software Engineering · Computer Science 2024-07-02 Nat McAleese , Rai Michael Pokorny , Juan Felipe Ceron Uribe , Evgenia Nitishinskaya , Maja Trebacz , Jan Leike

Logical reasoning is a core capability for large language models (LLMs), yet existing benchmarks that rely solely on final-answer accuracy fail to capture the quality of the reasoning process. To address this, we introduce FineLogic, a…

Computation and Language · Computer Science 2025-10-10 Yujun Zhou , Jiayi Ye , Zipeng Ling , Yufei Han , Yue Huang , Haomin Zhuang , Zhenwen Liang , Kehan Guo , Taicheng Guo , Xiangqi Wang , Xiangliang Zhang

Language models (LMs) have recently shown remarkable performance on reasoning tasks by explicitly generating intermediate inferences, e.g., chain-of-thought prompting. However, these intermediate inference steps may be inappropriate…

Computation and Language · Computer Science 2024-02-06 Debjit Paul , Mete Ismayilzada , Maxime Peyrard , Beatriz Borges , Antoine Bosselut , Robert West , Boi Faltings

LLMs can generate hardware descriptions from natural language specifications, but the resulting Verilog often contains width mismatches, combinational loops, and incomplete case logic that pass syntax checks yet fail in synthesis or…

Computation and Language · Computer Science 2026-05-13 Jing Xiong , Qi Han , Chenchen Ding , He Xiao , Zunhai Su , Chaofan Tao , Ngai Wong

Natural Language Generation (NLG) has made great progress in recent years due to the development of deep learning techniques such as pre-trained language models. This advancement has resulted in more fluent, coherent and even properties…

Computation and Language · Computer Science 2022-03-11 Wei Li , Wenhao Wu , Moye Chen , Jiachen Liu , Xinyan Xiao , Hua Wu

Cognitive computing models offer a formal and interpretable way to characterize human's deliberation and decision-making, yet their development remains labor-intensive. In this paper, we propose NL2CA, a novel method for auto-formalizing…

Artificial Intelligence · Computer Science 2025-12-23 Zihao Deng , Yijia Li , Renrui Zhang , Peijun Ye

Interactive proof assistants are computer programs carefully constructed to check a human-designed proof of a mathematical claim with high confidence in the implementation. However, this only validates truth of a formal claim, which may…

Programming Languages · Computer Science 2023-10-09 Colin S. Gordon , Sergey Matskevich