English
Related papers

Related papers: ImProver 2: Iteratively Self-Improving LMs for Neu…

200 papers

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 demonstrated impressive progress in complex reasoning tasks, largely driven by the Chain-of-Thought (CoT) paradigm, which decomposes difficult problems into intermediate steps. However, CoT reasoning…

Symbolic Computation · Computer Science 2026-05-26 Rui Wang , Zeming Wei , Yihao Zhang , Xiaokun Luan

Large Language Models (LLMs) have shown remarkable reasoning performance but struggle with multi-step deductive reasoning involving a series of rule application steps, especially when rules are presented non-sequentially. Our preliminary…

Computation and Language · Computer Science 2024-08-27 Siyuan Wang , Zhongyu Wei , Yejin Choi , Xiang Ren

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

SMLP: Symbolic Machine Learning Prover an open source tool for exploration and optimization of systems represented by machine learning models. SMLP uses symbolic reasoning for ML model exploration and optimization under verification and…

Machine Learning · Computer Science 2024-05-17 Franz Brauße , Zurab Khasidashvili , Konstantin Korovin

Language models frequently produce plausible yet incorrect reasoning traces that are difficult to verify. We investigate fine-tuning models to use Prolog as an external symbolic reasoning tool, training Qwen2.5-3B-Instruct with Group…

Computation and Language · Computer Science 2026-04-21 Niklas Mellgren , Peter Schneider-Kamp , Lukas Galke Poech

Large Language Models (LLMs) achieve strong performance on natural language tasks but remain unreliable in mathematical reasoning, frequently generating fluent yet logically inconsistent solutions. We present \textbf{NeuroProlog}, a…

Artificial Intelligence · Computer Science 2026-03-05 Pratibha Zunjare , Michael Hsiao

Recent advancements in large language models (LLMs) have spurred growing interest in automatic theorem proving using Lean4, where effective tree search methods are crucial for navigating the underlying large proof search spaces. While the…

Artificial Intelligence · Computer Science 2025-10-10 Ran Xin , Chenguang Xi , Jie Yang , Feng Chen , Hang Wu , Xia Xiao , Yifan Sun , Shen Zheng , Kai Shen

Formal theorem-proving benchmarks enable mechanically verifiable evaluation of mathematical reasoning in large language models. However, existing benchmarks mainly focus on Olympiad-style problems and algebraic domains, leaving…

Artificial Intelligence · Computer Science 2026-05-19 Wentao Long , Yunfei Zhang , Chenyi Li , Li Zhou , Chumin Sun , Zaiwen Wen

Effectively translating between natural language (NL) and formal logics like Linear Temporal Logic (LTL) requires expertise that limits formal verification's reach in safety-critical development. Template-based approaches sacrifice…

Artificial Intelligence · Computer Science 2026-05-25 Paapa Kwesi Quansah , Ernest Bonnah

Prompt optimization and fine-tuning are two major approaches to improve the performance of Large Language Models (LLMs). They enhance the capabilities of LLMs from complementary perspectives: the former through explicit natural language,…

Computation and Language · Computer Science 2026-03-03 Xiaohe Bo , Rui Li , Zexu Sun , Quanyu Dai , Zeyu Zhang , Zihang Tian , Xu Chen , Zhenhua Dong

Bias in Large Language Models (LLMs) poses significant risks to trustworthiness, manifesting primarily as stereotypical biases (e.g., gender or racial stereotypes) and structural biases (e.g., lexical overlap or position preferences).…

Computation and Language · Computer Science 2025-12-30 Xuan Feng , Bo An , Tianlong Gu , Liang Chang , Fengrui Hao , Peipeng Yu , Shuai Zhao

Large Language Models (LLMs) have shown strong performance on code understanding tasks, yet they fundamentally lack the ability to perform precise, exhaustive mathematical reasoning about program behavior. Existing benchmarks either focus…

Multimodal Large Language Models (MLLMs) have achieved impressive performances in mathematical reasoning, yet they remain vulnerable to visual hallucinations and logical inconsistencies that standard outcome-based supervision fails to…

Artificial Intelligence · Computer Science 2026-01-01 Peng Kuang , Xiangxiang Wang , Wentao Liu , Jian Dong , Kaidi Xu

Bilevel optimization has shown its utility across various machine learning settings, yet most algorithms in practice require second-order information, making it challenging to scale them up. Only recently, a paradigm of first-order…

Machine Learning · Computer Science 2025-05-27 Rui Pan , Dylan Zhang , Hanning Zhang , Xingyuan Pan , Minrui Xu , Jipeng Zhang , Renjie Pi , Xiaoyu Wang , Tong Zhang

Recent advances in large language models (LLMs) for mathematical reasoning have largely focused on tasks with easily verifiable final answers while generating and verifying natural language math proofs remains an open challenge. We identify…

Computation and Language · Computer Science 2026-03-03 Wenjie Ma , Andrei Cojocaru , Neel Kolhe , Bradley Louie , Robin Said Sharif , Haihan Zhang , Vincent Zhuang , Matei Zaharia , Sewon Min

We present Prover Agent, a novel AI agent for automated theorem proving that integrates large language models (LLMs) with a formal proof assistant, Lean. Prover Agent coordinates an informal reasoning LLM, a formal prover model, and…

Artificial Intelligence · Computer Science 2026-02-18 Kaito Baba , Chaoran Liu , Shuhei Kurita , Akiyoshi Sannai

Self-evolving scientific agents capable of conquering the hard tail of formal mathematics require Compositional Learning Behaviours (CLBs) -- the capacity to ground and recombine novel symbolic structures in context, beyond mere…

Computation and Language · Computer Science 2026-05-28 Kevin Yandoka Denamganaï

The use of formal language for deductive logical reasoning aligns well with language models (LMs), where translating natural language (NL) into first-order logic (FOL) and employing an external solver results in a verifiable and therefore…

Computation and Language · Computer Science 2026-01-15 Ramya Keerthy Thatikonda , Jiuzhou Han , Wray Buntine , Ehsan Shareghi

Despite impressive results on curated benchmarks, the practical impact of large language models (LLMs) on research-level neural theorem proving and proof autoformalization is still limited. We introduce RLMEval, an evaluation suite for…

Computation and Language · Computer Science 2025-10-30 Auguste Poiroux , Antoine Bosselut , Viktor Kunčak
‹ Prev 1 3 4 5 6 7 10 Next ›