Specification-Guided Repair of Arithmetic Errors in Dafny Programs using LLMs

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Wu, Valentina, Mendes, Alexandra, Abreu, Alexandre
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916940158599168
author Wu, Valentina
Mendes, Alexandra
Abreu, Alexandre
author_facet Wu, Valentina
Mendes, Alexandra
Abreu, Alexandre
contents Debugging and repairing faults when programs fail to formally verify can be complex and time-consuming. Automated Program Repair (APR) can ease this burden by automatically identifying and fixing faults. However, traditional APR techniques often rely on test suites for validation, but these may not capture all possible scenarios. In contrast, formal specifications provide strong correctness criteria, enabling more effective automated repair. In this paper, we present an APR tool for Dafny, a verification-aware programming language that uses formal specifications - including pre-conditions, post-conditions, and invariants - as oracles for fault localization and repair. Assuming the correctness of the specifications and focusing on arithmetic bugs, we localize faults through a series of steps, which include using Hoare logic to determine the state of each statement within the program, and applying Large Language Models (LLMs) to synthesize candidate fixes. The models considered are GPT-4o mini, Llama 3, Mistral 7B, and Llemma 7B. We evaluate our approach using DafnyBench, a benchmark of real-world Dafny programs. Our tool achieves 89.6% fault localization coverage and GPT-4o mini yields the highest repair success rate of 74.18%. These results highlight the potential of combining formal reasoning with LLM-based program synthesis for automated program repair.
format Preprint
id arxiv_https___arxiv_org_abs_2507_03659
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Specification-Guided Repair of Arithmetic Errors in Dafny Programs using LLMs
Wu, Valentina
Mendes, Alexandra
Abreu, Alexandre
Software Engineering
Programming Languages
Debugging and repairing faults when programs fail to formally verify can be complex and time-consuming. Automated Program Repair (APR) can ease this burden by automatically identifying and fixing faults. However, traditional APR techniques often rely on test suites for validation, but these may not capture all possible scenarios. In contrast, formal specifications provide strong correctness criteria, enabling more effective automated repair. In this paper, we present an APR tool for Dafny, a verification-aware programming language that uses formal specifications - including pre-conditions, post-conditions, and invariants - as oracles for fault localization and repair. Assuming the correctness of the specifications and focusing on arithmetic bugs, we localize faults through a series of steps, which include using Hoare logic to determine the state of each statement within the program, and applying Large Language Models (LLMs) to synthesize candidate fixes. The models considered are GPT-4o mini, Llama 3, Mistral 7B, and Llemma 7B. We evaluate our approach using DafnyBench, a benchmark of real-world Dafny programs. Our tool achieves 89.6% fault localization coverage and GPT-4o mini yields the highest repair success rate of 74.18%. These results highlight the potential of combining formal reasoning with LLM-based program synthesis for automated program repair.
title Specification-Guided Repair of Arithmetic Errors in Dafny Programs using LLMs
topic Software Engineering
Programming Languages
url https://arxiv.org/abs/2507.03659