ReFEree: Reference-Free and Fine-Grained Method for Evaluating Factual Consistency in Real-World Code Summarization

Suyoung Bae, CheolWon Na, Jaehoon Lee, Yumin Lee, YunSeok Choi, Jee-Hyong Lee


Abstract
As Large Language Models (LLMs) have become capable of generating long and descriptive code summaries, accurate and reliable evaluation of factual consistency has become a critical challenge. However, previous evaluation methods are primarily designed for short summaries of isolated code snippets. Consequently, they struggle to provide fine-grained evaluation of multi-sentence functionalities and fail to accurately assess dependency context commonly found in real-world code summaries.To address this, we propose ReFEree, a reference-free and fine-grained method for evaluating factual consistency in real-world code summaries. We define factual inconsistency criteria specific to code summaries and evaluate them at the segment level using these criteria along with dependency information. These segment-level results are then aggregated into a fine-grained score. We construct a code summarization benchmark with human-annotated factual consistency labels. The evaluation results demonstrate that ReFEree achieves the highest correlation with human judgment among 13 baselines, improving 15-18% over the previous state-of-the-art. Our code and data are available at https://github.com/bsy99615/ReFEree.git.
Anthology ID:
2026.acl-long.653
Volume:
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2026
Address:
San Diego, California, United States
Editors:
Maria Liakata, Viviane P. Moreira, Jiajun Zhang, David Jurgens
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
14352–14377
Language:
URL:
https://preview.aclanthology.org/ingest-acl/2026.acl-long.653/
DOI:
Bibkey:
Cite (ACL):
Suyoung Bae, CheolWon Na, Jaehoon Lee, Yumin Lee, YunSeok Choi, and Jee-Hyong Lee. 2026. ReFEree: Reference-Free and Fine-Grained Method for Evaluating Factual Consistency in Real-World Code Summarization. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 14352–14377, San Diego, California, United States. Association for Computational Linguistics.
Cite (Informal):
ReFEree: Reference-Free and Fine-Grained Method for Evaluating Factual Consistency in Real-World Code Summarization (Bae et al., ACL 2026)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingest-acl/2026.acl-long.653.pdf
Checklist:
 2026.acl-long.653.checklist.pdf