AI Heap
Published on

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

arXiv:2410.14748 - [arXiv,PDF]
Authors
  • Name
    Kishan Maharaj
  • Name
    Vitobha Munigala
  • Name
    Srikanth G. Tamilselvam
  • Name
    Prince Kumar
  • Name
    Sayandeep Sen
  • Name
    Palani Kodeswaran
  • Name
    Abhijit Mishra
  • Name
    Pushpak Bhattacharyya
  • Affiliation
    Indian Institute of Technology Bombay, Mumbai, India
  • Affiliation
    IBM Research India
  • Affiliation
    University of Texas at Austin, Texas, United States
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 summarization. However, LLMs are prone to hallucination-outputs that stray from intended meanings. Detecting hallucinations in code summarization is especially difficult due to the complex interplay between programming and natural languages. We introduce a first-of-its-kind dataset with $\sim$10K samples, curated specifically for hallucination detection in code summarization. We further propose a novel Entity Tracing Framework (ETF) that a) utilizes 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 effectiveness of the framework, leading to a 0.73 F1 score. This approach provides an interpretable method for detecting hallucinations by grounding entities, allowing us to evaluate summary accuracy.