VLP adds an NL documentation layer with trace-linked mismatch detection and derived formal checks to make human validation of LLM code feasible, lifting pass@1 from 28.7-73.2% to 65.4-93.5%.
Clarifygpt: A framework for enhancing llm-based code generation via requirements clarification,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.SE 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
CURE applies contrastive unlearning to reduce deprecated API usage in code LLMs and improve correct replacements on a benchmark dataset while preserving general performance.
citing papers explorer
-
Guiding Human Validation of LLM-Generated Code via Verifiable Literate Programming
VLP adds an NL documentation layer with trace-linked mismatch detection and derived formal checks to make human validation of LLM code feasible, lifting pass@1 from 28.7-73.2% to 65.4-93.5%.
-
Towards Knowledge Alignment in Code LLMs: Contrastive Unlearning for Evolving APIs
CURE applies contrastive unlearning to reduce deprecated API usage in code LLMs and improve correct replacements on a benchmark dataset while preserving general performance.