Single-Language Evidence Is Insufficient for Automated Logging: A Multilingual Benchmark and Empirical Study with LLMs

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhong, Renyi, Li, Yichen, Wu, Yulun, Kuang, Jinxi, Huo, Yintong, Lyu, Michael R.
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911605814460416
author Zhong, Renyi
Li, Yichen
Wu, Yulun
Kuang, Jinxi
Huo, Yintong
Lyu, Michael R.
author_facet Zhong, Renyi
Li, Yichen
Wu, Yulun
Kuang, Jinxi
Huo, Yintong
Lyu, Michael R.
contents Logging statements are central to debugging, failure diagnosis, and production observability, yet writing them requires developers to decide where to place a logging statement, which API and severity level to use, and what runtime information to expose. Automated logging aims to reduce this burden, but existing evidence remains dominated by Java-centric repository-snapshot dataset. It is therefore unclear whether conclusions about model behavior and model selection generalize across programming-language ecosystems or realistic code evolution. This paper presents MultiLogBench, a multilingual benchmark and empirical study spanning six programming language ecosystems. MultiLogBench contains 63,965 production-code repository-snapshot instances, 744 revision-history cases where developers introduce logging statements during maintenance, and a paired transformed revision-history branch for robustness analysis. Using seven contemporary large language models under a unified protocol, we evaluate logging-site localization, framework-anchor matching, severity prediction, message generation, variable recovery, and cascaded overall quality. Results show clear cross-language variation: framework-anchor matching is the most language-sensitive component, loop and nested-callable sites are the hardest structural contexts, and model rankings are stable only at the top tier. These patterns persist at a coarse level on revision-history data, while transformed inputs do not cause a broad same-direction performance collapse. Overall, MultiLogBench shows that robust claims about automated logging require multilingual evaluation and maintenance-oriented validation.
format Preprint
id arxiv_https___arxiv_org_abs_2604_17529
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Single-Language Evidence Is Insufficient for Automated Logging: A Multilingual Benchmark and Empirical Study with LLMs
Zhong, Renyi
Li, Yichen
Wu, Yulun
Kuang, Jinxi
Huo, Yintong
Lyu, Michael R.
Software Engineering
Logging statements are central to debugging, failure diagnosis, and production observability, yet writing them requires developers to decide where to place a logging statement, which API and severity level to use, and what runtime information to expose. Automated logging aims to reduce this burden, but existing evidence remains dominated by Java-centric repository-snapshot dataset. It is therefore unclear whether conclusions about model behavior and model selection generalize across programming-language ecosystems or realistic code evolution. This paper presents MultiLogBench, a multilingual benchmark and empirical study spanning six programming language ecosystems. MultiLogBench contains 63,965 production-code repository-snapshot instances, 744 revision-history cases where developers introduce logging statements during maintenance, and a paired transformed revision-history branch for robustness analysis. Using seven contemporary large language models under a unified protocol, we evaluate logging-site localization, framework-anchor matching, severity prediction, message generation, variable recovery, and cascaded overall quality. Results show clear cross-language variation: framework-anchor matching is the most language-sensitive component, loop and nested-callable sites are the hardest structural contexts, and model rankings are stable only at the top tier. These patterns persist at a coarse level on revision-history data, while transformed inputs do not cause a broad same-direction performance collapse. Overall, MultiLogBench shows that robust claims about automated logging require multilingual evaluation and maintenance-oriented validation.
title Single-Language Evidence Is Insufficient for Automated Logging: A Multilingual Benchmark and Empirical Study with LLMs
topic Software Engineering
url https://arxiv.org/abs/2604.17529