SiblingRepair: Sibling-Based Multi-Hunk Repair with Large Language Models

2026-05-07

AI Summary

This work addresses the challenge that existing automated program repair techniques struggle to accurately identify semantically related code locations (siblings) and generate consistent multi-hunk patches. The authors propose a novel large language model (LLM)-based approach that starts from spectrum-based suspicious locations, leverages token- and embedding-level matching to identify semantically similar sibling candidates, and employs synchronized and iterative strategies to produce semantically coherent multi-hunk patches. By circumventing reliance on commit history and abstract syntax tree (AST) structures, the method enables more flexible sibling discovery and cross-location patch generalization through the LLM’s capabilities. Experimental results on the Defects4J and GHRB benchmarks demonstrate that the proposed technique significantly outperforms current state-of-the-art methods in terms of repair effectiveness, efficiency, and component-wise contributions.

Abstract

Developers often make similar mistakes across code locations implementing related functionalities. These locations, called siblings, share similar issues and require similar fixes. Accurately identifying siblings and consistently repairing them are crucial for automated program repair. Hercules is a SOTA technique designed for sibling repair. However, it is limited by strong assumptions about sibling locations and commit-history availability, rigid AST-based sibling matching, and inflexible template-based patch generation. To address these limitations, we present SiblingRepair, a new LLM-based multi-hunk APR technique specialized for sibling repair. Starting from a suspicious location identified by spectrum-based fault localization, SiblingRepair searches for semantically related sibling candidates using token- and embedding-based code matching, without restricting discovery to failing-test coverage or commit history. It then uses an LLM to identify failure-relevant siblings and generate consistent patches through two complementary strategies: simultaneous repair, which jointly repairs siblings, and iterative repair, which progressively analyzes candidates for patch construction. SiblingRepair further preserves promising patches generated from earlier suspicious locations and combines them into generalized multi-hunk patches. We evaluate SiblingRepair on the Defects4J and GHRB benchmarks. The results show that SiblingRepair substantially outperforms SOTA multi-hunk repair techniques including Hercules. Our evaluation further demonstrates its repair efficiency, the effectiveness of its sibling detection and repair components, and limited impact of the LLM data leakage on the results. Overall, SiblingRepair advances automated sibling and general multi-hunk repair.

Problem

• sibling repair
• multi-hunk repair
• automated program repair
• large language models
• code matching

Innovation

• sibling-based repair
• large language models
• multi-hunk APR
• semantic code matching
• consistent patch generation