Source code summarization in the era of large language models

W Sun, Y Miao, Y Li, H Zhang, C Fang, Y Liu… - arxiv preprint arxiv …, 2024 - arxiv.org
To support software developers in understanding and maintaining programs, various
automatic (source) code summarization techniques have been proposed to generate a …

Calico: Automated Knowledge Calibration and Diagnosis for Elevating AI Mastery in Code Tasks

Y Qiu, J Hu, Q Zhang, H Yin - Proceedings of the 33rd ACM SIGSOFT …, 2024 - dl.acm.org
Recent advancements in large language models (LLMs) have exhibited promising
capabilities in addressing various tasks such as defect detection and program repair …

Malsight: Exploring malicious source code and benign pseudocode for iterative binary malware summarization

H Lu, H Peng, G Nan, J Cui, C Wang, W **… - arxiv preprint arxiv …, 2024 - arxiv.org
Binary malware summarization aims to automatically generate human-readable descriptions
of malware behaviors from executable files, facilitating tasks like malware cracking and …

Learning to Generate Structured Code Summaries from Hybrid Code Context

Z Zhou, M Li, H Yu, G Fan, P Yang… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Code summarization aims to automatically generate natural language descriptions for code,
and has become a rapidly expanding research area in the past decades. Unfortunately …

Enhancing Trust in LLM-Generated Code Summaries with Calibrated Confidence Scores

Y Virk, P Devanbu, T Ahmed - arxiv preprint arxiv:2404.19318, 2024 - arxiv.org
A good summary can often be very useful during program comprehension. While a brief,
fluent, and relevant summary can be helpful, it does require significant human effort to …

LLMs as Evaluators: A Novel Approach to Evaluate Bug Report Summarization

A Kumar, S Haiduc, PP Das, PP Chakrabarti - arxiv preprint arxiv …, 2024 - arxiv.org
Summarizing software artifacts is an important task that has been thoroughly researched.
For evaluating software summarization approaches, human judgment is still the most trusted …

Leveraging LLMs for Legacy Code Modernization: Challenges and Opportunities for LLM-Generated Documentation

C Diggs, M Doyle, A Madan, S Scott… - arxiv preprint arxiv …, 2024 - arxiv.org
Legacy software systems, written in outdated languages like MUMPS and mainframe
assembly, pose challenges in efficiency, maintenance, staffing, and security. While LLMs …

Resource-Efficient & Effective Code Summarization

S Afrin, J Call, KN Nguyen, O Chaparro… - arxiv preprint arxiv …, 2025 - arxiv.org
Code Language Models (CLMs) have demonstrated high effectiveness in automating
software engineering tasks such as bug fixing, code generation, and code documentation …

Good things come in three: Generating SO Post Titles with Pre-Trained Models, Self Improvement and Post Ranking

DA Le, B Thi-Mai-Anh, PT Nguyen… - Proceedings of the 18th …, 2024 - dl.acm.org
Background. Stack Overflow is a prominent Q&A forum, supporting developers in seeking
suitable resources on programming-related matters. Having high-quality question titles is an …

Explaining GitHub Actions Failures with Large Language Models: Challenges, Insights, and Limitations

P Valenzuela-Toledo, C Wu, S Hernandez… - arxiv preprint arxiv …, 2025 - arxiv.org
GitHub Actions (GA) has become the de facto tool that developers use to automate software
workflows, seamlessly building, testing, and deploying code. Yet when GA fails, it disrupts …