Structurally rich task descriptions make LLMs robust to prompt under-specification, and under-specification can enhance code correctness by disrupting misleading lexical or structural cues.
Automated repair of ambiguous problem descriptions for llm-based code generation,
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
fields
cs.SE 5years
2026 5representative citing papers
Orchid benchmark shows requirement ambiguity degrades LLM code generation performance across all models, with advanced models hit hardest, and LLMs rarely detect or resolve the ambiguity themselves.
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%.
SpecValidator detects lexical vagueness, under-specification, and syntax-formatting defects in LLM code-generation prompts with F1 0.804, outperforming GPT-5-mini and Claude Sonnet 4, and shows that under-specification is the most damaging defect type while richer benchmarks are more resilient.
REA-Coder improves LLM code generation by iteratively aligning requirements with model understanding and verifying outputs against the aligned spec.
citing papers explorer
-
When Prompt Under-Specification Improves Code Correctness: An Exploratory Study of Prompt Wording and Structure Effects on LLM-Based Code Generation
Structurally rich task descriptions make LLMs robust to prompt under-specification, and under-specification can enhance code correctness by disrupting misleading lexical or structural cues.
-
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%.
-
Bridging the Gap between User Intent and LLM: A Requirement Alignment Approach for Code Generation
REA-Coder improves LLM code generation by iteratively aligning requirements with model understanding and verifying outputs against the aligned spec.