LibEvoBench benchmark shows LLMs are version-oblivious on evolving APIs, with documentation helping but version specification not.
On Mitigating Code LLM Hallucinations with API Documentation
4 Pith papers cite this work, alongside 1 external citations. Polarity classification is still indexing.
4
Pith papers citing it
1
external citations · external index
citation-role summary
background 1
citation-polarity summary
fields
cs.SE 4roles
background 1polarities
background 1representative citing papers
A study of seven LLMs finds that realistic prompt variations such as one-character misspellings trigger library hallucinations in up to 26% of cases, fabricated names in up to 99%, and time-based prompts in up to 85%, and introduces LibHalluBench for evaluation.
A review of 114 studies creates taxonomies for code and data quality issues, formalizes 18 propagation mechanisms from training data defects to LLM-generated code defects, and synthesizes detection and mitigation techniques.
Mono2Sls automates monolith-to-serverless migration with static analysis and multi-stage LLM agents, achieving 100% deployment success and 66.1% end-to-end correctness on six benchmarks.
citing papers explorer
-
LibEvoBench: Probing Temporal Knowledge Stratification in Code Generation Models
LibEvoBench benchmark shows LLMs are version-oblivious on evolving APIs, with documentation helping but version specification not.
-
Library Hallucinations in LLM-Generated Code: A Risk Analysis Grounded in Developer Queries
A study of seven LLMs finds that realistic prompt variations such as one-character misspellings trigger library hallucinations in up to 26% of cases, fabricated names in up to 99%, and time-based prompts in up to 85%, and introduces LibHalluBench for evaluation.
-
Bridging Generation and Training: A Systematic Review of Quality Issues in LLMs for Code
A review of 114 studies creates taxonomies for code and data quality issues, formalizes 18 propagation mechanisms from training data defects to LLM-generated code defects, and synthesizes detection and mitigation techniques.
-
Mono2Sls: Automated Monolith-to-Serverless Migration via Multi-Stage Pipeline with Static Analysis
Mono2Sls automates monolith-to-serverless migration with static analysis and multi-stage LLM agents, achieving 100% deployment success and 66.1% end-to-end correctness on six benchmarks.