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

arXiv: https://arxiv.org/abs/2604.10520 · HTML: https://mlsanity.com/paper/2604.10520/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 44 references that are in the map.
- First posted on arXiv 12 Apr 2026.

## Builds on (most cited first, 25 of 25)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation](https://mlsanity.com/paper/2305.14251/) (2023)
- [DS-1000: A Natural and Reliable Benchmark for Data Science Code Generation](https://mlsanity.com/paper/2211.11501/) (2022)
- [Is ChatGPT a Good NLG Evaluator? A Preliminary Study](https://mlsanity.com/paper/2303.04048/) (2023)
- [Asking and Answering Questions to Evaluate the Factual Consistency of Summaries](https://mlsanity.com/paper/2004.04228/) (2020)
- [RepoBench: Benchmarking Repository-Level Code Auto-Completion Systems](https://mlsanity.com/paper/2306.03091/) (2023)
- [ClassEval: A Manually-Crafted Benchmark for Evaluating LLMs on Class-level Code Generation](https://mlsanity.com/paper/2308.01861/) (2023)
- [A Transformer-based Approach for Source Code Summarization](https://mlsanity.com/paper/2005.00653/) (2020)
- [LLM Hallucinations in Practical Code Generation: Phenomena, Mechanism, and Mitigation](https://mlsanity.com/paper/2409.20550/) (2024)
- [Execution-Based Evaluation for Open-Domain Code Generation](https://mlsanity.com/paper/2212.10481/) (2022)
- [FineSurE: Fine-grained Summarization Evaluation using LLMs](https://mlsanity.com/paper/2407.00908/) (2024)
- [RepoAgent: An LLM-Powered Open-Source Framework for Repository-level Code Documentation Generation](https://mlsanity.com/paper/2402.16667/) (2024)
- [CoCoMIC: Code Completion By Jointly Modeling In-file and Cross-file Context](https://mlsanity.com/paper/2212.10007/) (2022)
- [MEGAnno+: A Human-LLM Collaborative Annotation System](https://mlsanity.com/paper/2402.18050/) (2024)
- [Dataflow-Guided Retrieval Augmentation for Repository-Level Code Completion](https://mlsanity.com/paper/2405.19782/) (2024)
- [CodeHalu: Investigating Code Hallucinations in LLMs via Execution-based Verification](https://mlsanity.com/paper/2405.00253/) (2024)
- [Increasing the Speed and Accuracy of Data LabelingThrough an AI Assisted Interface](https://mlsanity.com/paper/2104.04122/) (2021)
- [Evaluating Code Summarization Techniques: A New Metric and an Empirical Characterization](https://mlsanity.com/paper/2312.15475/) (2023)
- [Identifying Inaccurate Descriptions in LLM-generated Code Comments via Test Execution](https://mlsanity.com/paper/2406.14836/) (2024)
- [CRScore: Grounding Automated Evaluation of Code Review Comments in Code Claims and Smells](https://mlsanity.com/paper/2409.19801/) (2024)
- [ETF: An Entity Tracing Framework for Hallucination Detection in Code Summaries](https://mlsanity.com/paper/2410.14748/) (2024)
- [PEANUT: A Human-AI Collaborative Tool for Annotating Audio-Visual Data](https://mlsanity.com/paper/2307.15167/) (2023)

## Built on by (most cited first, 1 of 1)

- [Remember Your Trace: Memory-Guided Long-Horizon Agentic Framework for Consistent and Hierarchical Repository-Level Code Documentation](https://mlsanity.com/paper/2605.14563/) (2026)

## Abstract (arXiv)

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.