English
Related papers

Related papers: Talk is Cheap, Logic is Hard: Benchmarking LLMs on…

200 papers

Large language models (LLMs) are increasingly used to generate requirements specifications, design documents, code, and test cases. In contrast, much less attention has been given to a more difficult assurance problem: statically verifying…

Software Engineering · Computer Science 2026-05-19 Zhi Quan Zhou , Dave Towey , Tsong Yueh Chen

Software specifications are essential for many Software Engineering (SE) tasks such as bug detection and test generation. Many existing approaches are proposed to extract the specifications defined in natural language form (e.g., comments)…

Software Engineering · Computer Science 2025-02-11 Danning Xie , Byungwoo Yoo , Nan Jiang , Mijung Kim , Lin Tan , Xiangyu Zhang , Judy S. Lee

Large Language Models (LLMs) can generate code, but can they generate fast code for complex, real-world software systems? In this study, we investigate this question using a dataset of 65 tasks mined from performance-critical open-source…

Software Engineering · Computer Science 2026-04-10 Lirong Yi , Gregory Gay , Philipp Leitner

Evaluation of large language model (LLM) outputs requires users to make critical judgments about the best outputs across various configurations. This process is costly and takes time given the large amounts of data. LLMs are increasingly…

Formalizing mathematical proofs using computerized verification languages like Lean 4 has the potential to significantly impact the field of mathematics, it offers prominent capabilities for advancing mathematical reasoning. However,…

Computation and Language · Computer Science 2024-11-11 Xichen Tang

In the past few years LLMs have emerged as a tool that can aid programmers by taking natural language descriptions and generating code based on it. However, the reliability of LLM code generation and current validation techniques for it are…

Programming Languages · Computer Science 2025-11-24 Aaron Councilman , David Jiahao Fu , Aryan Gupta , Chengxiao Wang , David Grove , Yu-Xiong Wang , Vikram Adve

In this paper we examine the limitations of Large Language Models (LLMs) for complex reasoning tasks. Although recent works have started to employ formal languages as an intermediate representation for reasoning tasks, they often face…

Logic in Computer Science · Computer Science 2024-08-07 Shashank Kirtania , Priyanshu Gupta , Arjun Radhakirshna

Assisting LLMs with code generation improved their performance on mathematical reasoning tasks. However, the evaluation of code-assisted LLMs is generally restricted to execution correctness, lacking a rigorous evaluation of their generated…

Computation and Language · Computer Science 2025-07-23 Zena Al-Khalili , Nick Howell , Dietrich Klakow

Large Language Models (LLMs) show promise in automated software engineering, yet their guarantee of correctness is frequently undermined by erroneous or hallucinated code. To enforce model honesty, formal verification requires LLMs to…

Software Engineering · Computer Science 2026-04-27 Md Erfan , Md Kamal Hossain Chowdhury , Ahmed Ryan , Md Rayhanur Rahman

Recent verification tools aim to make formal verification more accessible to software engineers by automating most of the verification process. However, annotating conventional programs with the formal specification and verification…

Software Engineering · Computer Science 2026-01-21 João Pascoal Faria , Emanuel Trigo , Vinicius Honorato , Rui Abreu

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,…

Computation and Language · Computer Science 2025-12-05 Hayden Moore , Asfahan Shah

Software testing plays a critical role in ensuring that systems behave as intended. However, existing automated testing approaches struggle to match the capabilities of human engineers due to key limitations such as test locality, lack of…

Software Engineering · Computer Science 2025-06-16 Kangping Xu , Yifan Luo , Yang Yuan , Andrew Chi-Chih Yao

We claim that LLMs can be paired with formal analysis methods to provide accessible, relevant feedback for HRI tasks. While logic specifications are useful for defining and assessing a task, these representations are not easily interpreted…

Robotics · Computer Science 2024-05-28 Emily Jensen , Sriram Sankaranarayanan , Bradley Hayes

Large Language Models (LLMs) have been shown to achieve breakthrough performance on complex logical reasoning tasks. Nevertheless, most existing research focuses on employing formal language to guide LLMs to derive reliable reasoning paths,…

Computation and Language · Computer Science 2025-05-23 Jin Jiang , Jianing Wang , Yuchen Yan , Yang Liu , Jianhua Zhu , Mengdi Zhang , Xunliang Cai , Liangcai Gao

Background: Manual testing is vital for detecting issues missed by automated tests, but specifying accurate verifications is challenging. Aims: This study aims to explore the use of Large Language Models (LLMs) to produce verifications for…

Test cases are essential for validating the reliability and quality of software applications. Recent studies have demonstrated the capability of Large Language Models (LLMs) to generate useful test cases for given source code. However, the…

Software Engineering · Computer Science 2025-01-03 Shuzheng Gao , Chaozheng Wang , Cuiyun Gao , Xiaoqian Jiao , Chun Yong Chong , Shan Gao , Michael Lyu

Fully automated verification of large-scale software and hardware systems is arguably the holy grail of formal methods. Large language models (LLMs) have recently demonstrated their potential for enhancing the degree of automation in formal…

Software Engineering · Computer Science 2025-08-21 Zhongyi Wang , Tengjie Lin , Mingshuai Chen , Mingqi Yang , Haokun Li , Xiao Yi , Shengchao Qin , Jianwei Yin

Reliable verification of proofs remains a bottleneck for training and evaluating AI systems on hard mathematical reasoning. Fully formal proofs, in languages like Lean, are easy to verify because they are unambiguous and modular. Most…

Logic in Computer Science · Computer Science 2026-05-21 Slim Barkallah , Luke Bailey , Kaiyue Wen , Mohammed Abouzaid , Tengyu Ma

Previous work adopts large language models (LLMs) as evaluators to evaluate natural language process (NLP) tasks. However, certain shortcomings, e.g., fairness, scope, and accuracy, persist for current LLM evaluators. To analyze whether…

Computation and Language · Computer Science 2025-01-22 Qintong Li , Leyang Cui , Lingpeng Kong , Wei Bi

Most existing code Large Language Model (LLM) benchmarks, e.g., EvalPlus, focus on the code generation tasks. Namely, they contain a natural language description of a problem and ask the LLM to write code to solve the problem. We argue that…

Software Engineering · Computer Science 2024-07-22 Fusen He , Juan Zhai , Minxue Pan