Saved in:
Bibliographic Details
Main Authors: Li, Yufei, Chen, Simin, Guo, Yanghong, Yang, Wei, Dong, Yue, Liu, Cong
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2402.05939
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929238115876864
author Li, Yufei
Chen, Simin
Guo, Yanghong
Yang, Wei
Dong, Yue
Liu, Cong
author_facet Li, Yufei
Chen, Simin
Guo, Yanghong
Yang, Wei
Dong, Yue
Liu, Cong
contents Large Language Models (LLMs) have been widely employed in programming language analysis to enhance human productivity. Yet, their reliability can be compromised by various code distribution shifts, leading to inconsistent outputs. While probabilistic methods are known to mitigate such impact through uncertainty calibration and estimation, their efficacy in the language domain remains underexplored compared to their application in image-based tasks. In this work, we first introduce a large-scale benchmark dataset, incorporating three realistic patterns of code distribution shifts at varying intensities. Then we thoroughly investigate state-of-the-art probabilistic methods applied to CodeLlama using these shifted code snippets. We observe that these methods generally improve the uncertainty awareness of CodeLlama, with increased calibration quality and higher uncertainty estimation~(UE) precision. However, our study further reveals varied performance dynamics across different criteria (e.g., calibration error vs misclassification detection) and trade-off between efficacy and efficiency, highlighting necessary methodological selection tailored to specific contexts.
format Preprint
id arxiv_https___arxiv_org_abs_2402_05939
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Uncertainty Awareness of Large Language Models Under Code Distribution Shifts: A Benchmark Study
Li, Yufei
Chen, Simin
Guo, Yanghong
Yang, Wei
Dong, Yue
Liu, Cong
Software Engineering
Computation and Language
Machine Learning
Large Language Models (LLMs) have been widely employed in programming language analysis to enhance human productivity. Yet, their reliability can be compromised by various code distribution shifts, leading to inconsistent outputs. While probabilistic methods are known to mitigate such impact through uncertainty calibration and estimation, their efficacy in the language domain remains underexplored compared to their application in image-based tasks. In this work, we first introduce a large-scale benchmark dataset, incorporating three realistic patterns of code distribution shifts at varying intensities. Then we thoroughly investigate state-of-the-art probabilistic methods applied to CodeLlama using these shifted code snippets. We observe that these methods generally improve the uncertainty awareness of CodeLlama, with increased calibration quality and higher uncertainty estimation~(UE) precision. However, our study further reveals varied performance dynamics across different criteria (e.g., calibration error vs misclassification detection) and trade-off between efficacy and efficiency, highlighting necessary methodological selection tailored to specific contexts.
title Uncertainty Awareness of Large Language Models Under Code Distribution Shifts: A Benchmark Study
topic Software Engineering
Computation and Language
Machine Learning
url https://arxiv.org/abs/2402.05939