ReDef creates a revert-anchored dataset of 3,164 defective and 10,268 clean code modifications and shows that code language models perform better with diff encodings but maintain stable performance under counterfactual perturbations, indicating reliance on superficial cues.
Automatic code summarization via chatgpt: How far are we?
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
A multi-agent bottom-up framework (summarizer + keyword extractor + QA) improves hierarchical code-summary consistency by ~8% and normalized keyword coverage by up to 38% over structured prompting baselines.
CodeWiki presents a unified framework for repository-level documentation across seven languages using hierarchical decomposition, recursive multi-agent processing, and multi-modal synthesis, outperforming DeepWiki by 4.73% on CodeWikiBench.
A systematic review that categorizes prompting strategies for LLM-based code summarization, assesses their effectiveness, and identifies gaps in research and evaluation practices.
Data-influence-score filtering using validation-set loss on downstream coding tasks improves Code-LLM performance, with the most beneficial training data varying significantly across different programming tasks.
citing papers explorer
-
ReDef: Do Code Language Models Truly Understand Code Changes for Just-in-Time Software Defect Prediction?
ReDef creates a revert-anchored dataset of 3,164 defective and 10,268 clean code modifications and shows that code language models perform better with diff encodings but maintain stable performance under counterfactual perturbations, indicating reliance on superficial cues.
-
Agent4cs: A Multi-agent System for Code Summarization in Large Hierarchical Codebases
A multi-agent bottom-up framework (summarizer + keyword extractor + QA) improves hierarchical code-summary consistency by ~8% and normalized keyword coverage by up to 38% over structured prompting baselines.
-
CodeWiki: Evaluating AI's Ability to Generate Holistic Documentation for Large-Scale Codebases
CodeWiki presents a unified framework for repository-level documentation across seven languages using hierarchical decomposition, recursive multi-agent processing, and multi-modal synthesis, outperforming DeepWiki by 4.73% on CodeWikiBench.
-
Prompt-Driven Code Summarization: A Systematic Literature Review
A systematic review that categorizes prompting strategies for LLM-based code summarization, assesses their effectiveness, and identifies gaps in research and evaluation practices.
-
An Empirical Study on Influence-Based Pretraining Data Selection for Code Large Language Models
Data-influence-score filtering using validation-set loss on downstream coding tasks improves Code-LLM performance, with the most beneficial training data varying significantly across different programming tasks.