SimSCOOD: Systematic Analysis of Out-of-Distribution Generalization in Fine-tuned Source Code Models

Hossein Hajipour, Ning Yu, Cristian-Alexandru Staicu, Mario Fritz


Abstract
Large code datasets have become increasingly accessible for pre-training source code models. However, for the fine-tuning phase, obtaining representative training data that fully covers the code distribution for specific downstream tasks remains challenging due to the task-specific nature and limited labeling resources. These lead to out-of-distribution (OOD) generalization issues with unexpected model inference behaviors that have not been systematically studied yet.In this paper, we contribute the first systematic approach that simulates various OOD scenarios along different dimensions of source code data properties and study the fine-tuned model behaviors in such scenarios. We investigate the behaviors of models under different fine-tuning methodologies, including full fine-tuning and Low-Rank Adaptation (LoRA) fine-tuning methods. Our comprehensive analysis, conducted on four state-of-the-art pretrained models and applied to two code generation tasks, exposes multiple failure modes attributed to OOD generalization issues.
Anthology ID:
2024.findings-naacl.90
Volume:
Findings of the Association for Computational Linguistics: NAACL 2024
Month:
June
Year:
2024
Address:
Mexico City, Mexico
Editors:
Kevin Duh, Helena Gomez, Steven Bethard
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1400–1416
Language:
URL:
https://aclanthology.org/2024.findings-naacl.90
DOI:
Bibkey:
Cite (ACL):
Hossein Hajipour, Ning Yu, Cristian-Alexandru Staicu, and Mario Fritz. 2024. SimSCOOD: Systematic Analysis of Out-of-Distribution Generalization in Fine-tuned Source Code Models. In Findings of the Association for Computational Linguistics: NAACL 2024, pages 1400–1416, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
SimSCOOD: Systematic Analysis of Out-of-Distribution Generalization in Fine-tuned Source Code Models (Hajipour et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-naacl.90.pdf
Copyright:
 2024.findings-naacl.90.copyright.pdf