Healer uses LLMs to dynamically generate and execute runtime error-handling code, with GPT-4 recovering from 72.8% of errors across four datasets.
arXiv preprint arXiv:2403.07506 (2024)
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 6roles
background 1polarities
background 1representative citing papers
Natural backdoors are prevalent in CodeLMs; the authors propose ScanNBT to detect them after analyzing differences from injected backdoors, transferability, and causes.
DuCodeMark watermarks code datasets using AST style transformations and repressible poisons for both source-code and decompilation tasks, verified by t-test, with high stealth and a 28.6% performance drop if removed.
Empirical study on five LLMs finds pretrained-to-aligned paths yield bigger gains over baseline than finetuned-to-aligned paths, though absolute accuracy remains lower for pretrained starts.
A survey of user studies on LLM use in programming that identifies interaction behaviors, mixed benefits and weaknesses, and factors influencing human and task performance.
A systematic literature review that organizes recent work on LLMs for code generation into a taxonomy covering data curation, model advances, evaluations, ethics, environmental impact, and applications, with benchmark comparisons.
citing papers explorer
-
Towards Agentic Runtime Healing
Healer uses LLMs to dynamically generate and execute runtime error-handling code, with GPT-4 recovering from 72.8% of errors across four datasets.
-
Securing Code Understanding: Detecting Natural Backdoor Vulnerability in Code Language Models
Natural backdoors are prevalent in CodeLMs; the authors propose ScanNBT to detect them after analyzing differences from injected backdoors, transferability, and causes.
-
DuCodeMark: Dual-Purpose Code Dataset Watermarking via Style-Aware Watermark-Poison Design
DuCodeMark watermarks code datasets using AST style transformations and repressible poisons for both source-code and decompilation tasks, verified by t-test, with high stealth and a 28.6% performance drop if removed.
-
Reward-Free Code Alignment from Pretrained or Fine-Tuned LLM: Unpacking the Trade-offs for Code Generation
Empirical study on five LLMs finds pretrained-to-aligned paths yield bigger gains over baseline than finetuned-to-aligned paths, though absolute accuracy remains lower for pretrained starts.
-
Understanding the Human-LLM Dynamic: A Literature Survey of LLM Use in Programming Tasks
A survey of user studies on LLM use in programming that identifies interaction behaviors, mixed benefits and weaknesses, and factors influencing human and task performance.
-
A Survey on Large Language Models for Code Generation
A systematic literature review that organizes recent work on LLMs for code generation into a taxonomy covering data curation, model advances, evaluations, ethics, environmental impact, and applications, with benchmark comparisons.