Amal Akli
2 papers · Latest:
Software Engineering
When Prompt Under-Specification Improves Code Correctness: An Exploratory Study of Prompt Wording and Structure Effects on LLM-Based Code Generation
Under-specification in LLM prompts can surprisingly improve code correctness, particularly with structurally rich task descriptions, challenging prior assumptions.
2604.24712
Software EngineeringDefective Task Descriptions in LLM-Based Code Generation: Detection and Analysis
Introduces SpecValidator, a lightweight classifier that effectively detects defective task descriptions in LLM-based code generation, outperforming larger models.
2604.24703
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.