ETF: An Entity Tracing Framework for Hallucination Detection in Code Summaries

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Maharaj, Kishan, Munigala, Vitobha, Tamilselvam, Srikanth G., Kumar, Prince, Sen, Sayandeep, Kodeswaran, Palani, Mishra, Abhijit, Bhattacharyya, Pushpak
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914024840495104
author Maharaj, Kishan
Munigala, Vitobha
Tamilselvam, Srikanth G.
Kumar, Prince
Sen, Sayandeep
Kodeswaran, Palani
Mishra, Abhijit
Bhattacharyya, Pushpak
author_facet Maharaj, Kishan
Munigala, Vitobha
Tamilselvam, Srikanth G.
Kumar, Prince
Sen, Sayandeep
Kodeswaran, Palani
Mishra, Abhijit
Bhattacharyya, Pushpak
contents Recent advancements in large language models (LLMs) have significantly enhanced their ability to understand both natural language and code, driving their use in tasks like natural language-to-code (NL2Code) and code summarisation. However, LLMs are prone to hallucination, outputs that stray from intended meanings. Detecting hallucinations in code summarisation is especially difficult due to the complex interplay between programming and natural languages. We introduce a first-of-its-kind dataset, CodeSumEval, with ~10K samples, curated specifically for hallucination detection in code summarisation. We further propose a novel Entity Tracing Framework (ETF) that a) utilises static program analysis to identify code entities from the program and b) uses LLMs to map and verify these entities and their intents within generated code summaries. Our experimental analysis demonstrates the framework's effectiveness, leading to a 73% F1 score. The proposed approach provides a method for detecting hallucinations by tracing entities from the summary to the code, allowing us to evaluate summary accuracy and localise the error within the summary.
format Preprint
id arxiv_https___arxiv_org_abs_2410_14748
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle ETF: An Entity Tracing Framework for Hallucination Detection in Code Summaries
Maharaj, Kishan
Munigala, Vitobha
Tamilselvam, Srikanth G.
Kumar, Prince
Sen, Sayandeep
Kodeswaran, Palani
Mishra, Abhijit
Bhattacharyya, Pushpak
Software Engineering
Artificial Intelligence
Computation and Language
Recent advancements in large language models (LLMs) have significantly enhanced their ability to understand both natural language and code, driving their use in tasks like natural language-to-code (NL2Code) and code summarisation. However, LLMs are prone to hallucination, outputs that stray from intended meanings. Detecting hallucinations in code summarisation is especially difficult due to the complex interplay between programming and natural languages. We introduce a first-of-its-kind dataset, CodeSumEval, with ~10K samples, curated specifically for hallucination detection in code summarisation. We further propose a novel Entity Tracing Framework (ETF) that a) utilises static program analysis to identify code entities from the program and b) uses LLMs to map and verify these entities and their intents within generated code summaries. Our experimental analysis demonstrates the framework's effectiveness, leading to a 73% F1 score. The proposed approach provides a method for detecting hallucinations by tracing entities from the summary to the code, allowing us to evaluate summary accuracy and localise the error within the summary.
title ETF: An Entity Tracing Framework for Hallucination Detection in Code Summaries
topic Software Engineering
Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2410.14748