{
  "id": 4000,
  "url": "https://arxiv.org/abs/2605.20410v1",
  "title": "Mechanics of Bias and Reasoning: Interpreting the Impact of Chain-of-Thought Prompting on Gender Bias in LLMs",
  "summary": "Large language models (LLMs) are increasingly deployed in socially sensitive settings despite substantial documentation that they encode gender biases. Chain-of-Thought (CoT) prompting has been proposed as a bias-mitigation approach. However, existing evaluations primarily focus on changes in LLM benchmark performance, providing limited insight into whether apparent bias reductions reflect meaningful changes in a model's internal mechanisms. In this work, we investigate how CoT prompting affects",
  "authors": "Edie Pearman, Sophia Osborne, Mira Kandlikar-Bloch, Mina Arzaghi, Florian Carichon, Golnoosh Farnadi",
  "category": "research",
  "topics": "bias-fairness,finance-investment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-05-19T19:05:13.000Z",
  "fetched_at": "2026-07-14T16:30:41.580Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/4000",
  "original_url": "https://arxiv.org/abs/2605.20410v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}