AI ethics evidence index Search
Source-linked daily record
Evidence record 44 · automatically gathered

Mitigating LLM Sycophancy in Code Smell Detection Using Evidence-Guided Reasoning Prompts

Large Language Models (LLMs) are increasingly used for code smell detection tasks due to their ability to interpret program semantics. However, their reliability in this context remains poorly explored, particularly under varying prompt conditions where model predictions may be influenced by external cues rather than code characteristics. One such limitation is sycophancy bias, where models tend to align their outputs with user-provided assumptions instead of performing objective analysis. In th

Record details

Published: 11 July 2026
Source: arXiv
Category: Research
Topics: Bias & fairness
Retrieved: 14 July 2026

source-onlyevidence status

These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.

Shared topic: Bias & fairness

How Data Narratives Go Wrong: A Taxonomy of Issues Across the Data Communication Process

arXiv cs.HC · 12 July 2026

Shared topic: Bias & fairness

Balancing fairness and influence spread in social networks: a multi-objective evolutionary approach

Artificial Intelligence Review · 11 July 2026

Shared topic: Bias & fairness

Optimizing ARDL Models for Retail Sales Forecasting and Fair Pricing

arXiv fairness query · 10 July 2026

Shared topic: Bias & fairness

What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection

arXiv · 10 July 2026

Shared topic: Bias & fairness

Normative Alignment of Recommender Systems via Internal Label Shift

arXiv fairness query · 12 July 2026

Shared topic: Bias & fairness

Teacher-regulated generative AI support, student agency, and perceived learning gains in higher education: the moderating role of perceived fairness

Frontiers in Artificial Intelligence · 13 July 2026

How to cite this record

ethics.ai (11 July 2026), “Mitigating LLM Sycophancy in Code Smell Detection Using Evidence-Guided Reasoning Prompts,” evidence record 44, https://ethics.ai/record/44 (originally published by arXiv).

JSON

Use and limitations

This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.