When Prompts Go Wrong: Evaluating Code Model Robustness to Ambiguous, Contradictory, and Incomplete Task Descriptions

Documenti analoghi

• Defective Task Descriptions in LLM-Based Code Generation: Detection and Analysis
  di: Akli, Amal, et al.
  Pubblicazione: (2026)
• One Model, Many Skills: Parameter-Efficient Fine-Tuning for Multitask Code Analysis
  di: Akli, Amal, et al.
  Pubblicazione: (2026)
• Software Fairness: An Analysis and Survey
  di: Soremekun, Ezekiel, et al.
  Pubblicazione: (2022)
• Going Further: Flatness at the Rescue of Early Stopping for Adversarial Example Transferability
  di: Gubri, Martin, et al.
  Pubblicazione: (2023)
• GenCode: A Generic Data Augmentation Framework for Boosting Deep Learning-Based Code Understanding
  di: Dong, Zeming, et al.
  Pubblicazione: (2024)