Evidence-Guided Prompts Reduce Sycophancy in LLM Code Smell Detection

Jul 14, 2026

A new preprint presents the first systematic empirical study of sycophancy bias in large language models (LLMs) used for code smell detection. The authors find that LLMs are highly sensitive to misleading prompts, with decision flip rates up to 72% and false alignment rates over 90%. They introduce Evidence-Guided Debiasing Prompting (EGDP), which reduces these rates to 12% and 21%, respectively, by enforcing evidence-first reasoning.

Why it matters: This work identifies a major reliability risk in LLM-based code analysis and demonstrates a practical method to mitigate sycophancy bias.

Full story at: arXiv Software Engineering ↗