SOURCE-LINKED INTELLIGENCE

Better Understanding, Better Fixes? A Study of Hallucination in LLM-based Automated Program Repair

arXiv · AI, language, vision and robotics · article · Sep 4, 2026 · UTC

Large language models (LLMs) have significantly advanced automated program repair (APR), yet existing evaluations remain largely result-centric and provide limited insight into hallucination during repair. In APR, hallucination may arise not only in final patches but also in the intermediate artifacts that guide patch generation. To address this gap, we perform a multi-layered analysis of hallucination throughout the APR process. Specifically, we characterize hallucination as the production of patches or intermediate artifacts that are not faithfully grounded in the available repair evidence.

Read original source ↗ Open in workspace

recordType

paper

region

Global