中文
相关论文

相关论文: What are the Right Symmetries for Formal Theorem P…

200 篇论文

Evaluating factual correctness of LLM generated natural language explanations grounded in time series data remains an open challenge. Although modern models generate textual interpretations of numerical signals, existing evaluation methods…

人工智能 · 计算机科学 2026-04-03 Preetham Sivalingam , Murari Mandal , Saurabh Deshpande , Dhruv Kumar

Large language models (LLMs) have recently shown strong performance on mathematical benchmarks. At the same time, they are prone to hallucination and sycophancy, often providing convincing but flawed proofs for incorrect mathematical…

人工智能 · 计算机科学 2025-10-07 Ivo Petrov , Jasper Dekoninck , Martin Vechev

Large Language Models (LLMs) demonstrate strong mathematical problem-solving abilities but frequently fail on problems that deviate syntactically from their training distribution. We identify a systematic failure mode, syntactic blind…

计算与语言 · 计算机科学 2025-10-03 Dane Williamson , Yangfeng Ji , Matthew Dwyer

Can autoregressive large language models (LLMs) learn consistent probability distributions when trained on sequences in different token orders? We prove formally that for any well-defined probability distribution, sequence perplexity is…

计算与语言 · 计算机科学 2025-05-14 Xiaoliang Luo , Xinyi Xu , Michael Ramscar , Bradley C. Love

Despite the success of large language models (LLMs), the task of theorem proving still remains one of the hardest reasoning tasks that is far from being fully solved. Prior methods using language models have demonstrated promising results,…

Despite significant advancements in the general capability of large language models (LLMs), they continue to struggle with consistent and accurate reasoning, especially in complex tasks such as mathematical and code reasoning. One key…

机器学习 · 计算机科学 2024-10-10 Zhenwen Liang , Ye Liu , Tong Niu , Xiangliang Zhang , Yingbo Zhou , Semih Yavuz

This paper presents a method to analyze the inference patterns used by Large Language Models (LLMs) for judgment in a case study on legal LLMs, so as to identify potential incorrect representations of the LLM, according to human domain…

人工智能 · 计算机科学 2025-05-21 Lu Chen , Yuxuan Huang , Yixing Li , Dongrui Liu , Qihan Ren , Shuai Zhao , Kun Kuang , Zilong Zheng , Quanshi Zhang

Large Language Models (LLMs) display strikingly different generalization behaviors: supervised fine-tuning (SFT) often narrows capability, whereas reinforcement-learning (RL) tuning tends to preserve it. The reasons behind this divergence…

机器学习 · 计算机科学 2026-01-01 Haoyue Bai , Yiyou Sun , Wenjie Hu , Shi Qiu , Maggie Ziyu Huan , Peiyang Song , Robert Nowak , Dawn Song

Large Language Models (LLMs) have recently emerged as powerful tools for autoformalization. Despite their impressive performance, these models can still struggle to produce grounded and verifiable formalizations. Recent work in text-to-SQL,…

计算与语言 · 计算机科学 2025-12-05 Hayden Moore , Asfahan Shah

Recent large language models (LLMs) perform strongly on mathematical benchmarks yet often misapply lemmas, importing conclusions without validating assumptions. We formalize lemma$-$judging as a structured prediction task: given a statement…

计算与语言 · 计算机科学 2026-02-03 Zhikun Xu , Xiaodong Yu , Ben Zhou , Jiang Liu , Jialian Wu , Ze Wang , Ximeng Sun , Hao Chen , Zicheng Liu

Mechanical reasoning is a key area of research that lies at the crossroads of mathematical logic and artificial intelligence. The main aim to develop mechanical reasoning systems (also known as theorem provers) was to enable mathematicians…

软件工程 · 计算机科学 2019-12-09 M. Saqib Nawaz , Moin Malik , Yi Li , Meng Sun , M. Ikram Ullah Lali

Representation theorems for formal systems often take the form of an inductive translation that satisfies certain invariants, which are proved inductively. Theory morphisms and logical relations are common patterns of such inductive…

计算机科学中的逻辑 · 计算机科学 2026-03-20 Thomas Traversié , Florian Rabe

Large language models (LLMs) are trained on extensive datasets that encapsulate substantial world knowledge. However, their outputs often include confidently stated inaccuracies. Earlier works suggest that LLMs encode truthfulness as a…

计算与语言 · 计算机科学 2025-06-03 Yuntai Bao , Xuhong Zhang , Tianyu Du , Xinkui Zhao , Zhengwen Feng , Hao Peng , Jianwei Yin

Requirements over strings, commonly represented using natural language (NL), are particularly relevant for software systems due to their heavy reliance on string data manipulation. While individual requirements can usually be analyzed…

软件工程 · 计算机科学 2025-06-23 Boqi Chen , Aren A. Babikian , Shuzhao Feng , Dániel Varró , Gunter Mussbacher

Large language models (LLMs) often struggle with complex logical reasoning due to logical inconsistencies and the inherent difficulty of such reasoning. We use Lean, a theorem proving framework, to address these challenges. By formalizing…

计算与语言 · 计算机科学 2024-03-21 Dongwei Jiang , Marcio Fonseca , Shay B. Cohen

In many high-risk machine learning applications it is essential for a model to indicate when it is uncertain about a prediction. While large language models (LLMs) can reach and even surpass human-level accuracy on a variety of benchmarks,…

计算与语言 · 计算机科学 2024-06-06 Evan Becker , Stefano Soatto

While Large language models (LLMs) have proved able to address some complex reasoning tasks, we also know that they are highly sensitive to input variation, which can lead to different solution paths and final answers. Answer consistency…

计算与语言 · 计算机科学 2025-03-05 Huiyuan Lai , Xiao Zhang , Malvina Nissim

The growing awareness of safety concerns in large language models (LLMs) has sparked considerable interest in the evaluation of safety. This study investigates an under-explored issue about the evaluation of LLMs, namely the substantial…

计算与语言 · 计算机科学 2024-04-02 Yixu Wang , Yan Teng , Kexin Huang , Chengqi Lyu , Songyang Zhang , Wenwei Zhang , Xingjun Ma , Yu-Gang Jiang , Yu Qiao , Yingchun Wang

As large language models (LLMs) are increasing integrated into fact-checking pipelines, formal logic is often proposed as a rigorous means by which to mitigate bias, errors and hallucinations in these models' outputs. For example, some…

计算与语言 · 计算机科学 2026-04-28 Jason Chan , Robert Gaizauskas , Zhixue Zhao

Large language models (LLMs) often generate content with unsupported or unverifiable content, known as "hallucinations." To address this, retrieval-augmented LLMs are employed to include citations in their content, grounding the content in…

信息检索 · 计算机科学 2024-08-23 Weijia Zhang , Mohammad Aliannejadi , Jiahuan Pei , Yifei Yuan , Jia-Hong Huang , Evangelos Kanoulas