Do Machines and Humans Focus on Similar Code? Exploring Explainability of Large Language Models in Code Summarization

February 22, 2024 Β· Declared Dead Β· πŸ› IEEE International Conference on Program Comprehension

πŸ‘» CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Jiliang Li, Yifan Zhang, Zachary Karas, Collin McMillan, Kevin Leach, Yu Huang arXiv ID 2402.14182 Category cs.SE: Software Engineering Cross-listed cs.AI Citations 21 Venue IEEE International Conference on Program Comprehension Last Checked 4 months ago
Abstract
Recent language models have demonstrated proficiency in summarizing source code. However, as in many other domains of machine learning, language models of code lack sufficient explainability. Informally, we lack a formulaic or intuitive understanding of what and how models learn from code. Explainability of language models can be partially provided if, as the models learn to produce higher-quality code summaries, they also align in deeming the same code parts important as those identified by human programmers. In this paper, we report negative results from our investigation of explainability of language models in code summarization through the lens of human comprehension. We measure human focus on code using eye-tracking metrics such as fixation counts and duration in code summarization tasks. To approximate language model focus, we employ a state-of-the-art model-agnostic, black-box, perturbation-based approach, SHAP (SHapley Additive exPlanations), to identify which code tokens influence that generation of summaries. Using these settings, we find no statistically significant relationship between language models' focus and human programmers' attention. Furthermore, alignment between model and human foci in this setting does not seem to dictate the quality of the LLM-generated summaries. Our study highlights an inability to align human focus with SHAP-based model focus measures. This result calls for future investigation of multiple open questions for explainable language models for code summarization and software engineering tasks in general, including the training mechanisms of language models for code, whether there is an alignment between human and model attention on code, whether human attention can improve the development of language models, and what other model focus measures are appropriate for improving explainability.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Software Engineering

Died the same way β€” πŸ‘» Ghosted