Source code summarization in the era of large language models
To support software developers in understanding and maintaining programs, various
automatic (source) code summarization techniques have been proposed to generate a …
automatic (source) code summarization techniques have been proposed to generate a …
Calico: Automated Knowledge Calibration and Diagnosis for Elevating AI Mastery in Code Tasks
Recent advancements in large language models (LLMs) have exhibited promising
capabilities in addressing various tasks such as defect detection and program repair …
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 …
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 …
and has become a rapidly expanding research area in the past decades. Unfortunately …
Enhancing Trust in LLM-Generated Code Summaries with Calibrated Confidence Scores
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 …
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
Summarizing software artifacts is an important task that has been thoroughly researched.
For evaluating software summarization approaches, human judgment is still the most trusted …
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Legacy software systems, written in outdated languages like MUMPS and mainframe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 …
assembly, pose challenges in efficiency, maintenance, staffing, and security. While LLMs …
Resource-Efficient & Effective Code Summarization
Code Language Models (CLMs) have demonstrated high effectiveness in automating
software engineering tasks such as bug fixing, code generation, and code documentation …
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 …
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 …
workflows, seamlessly building, testing, and deploying code. Yet when GA fails, it disrupts …