{
  "id": 4490,
  "url": "https://arxiv.org/abs/2606.12426v1",
  "title": "Two Wrongs, No Right: Auditing Social-Desirability Bias in LLM Annotators for Computational Social Science",
  "summary": "LLM annotators are increasingly used in computational social science (CSS), but it is unclear whether their alignment-shaped errors preserve the empirical conclusions a researcher would report. We audit three open-source 7B instruction-tuned models (Zephyr, Mistral-Instruct, Qwen2.5-Instruct) across six TweetEval tasks under four prompt conditions (72 cells) and find that social-desirability failures do not run in a single direction. Zephyr exhibits leniency bias, systematically under-applying h",
  "authors": "Varun Kotte",
  "category": "research",
  "topics": "bias-fairness,safety-alignment,transparency",
  "orgs": "mistral",
  "regions": null,
  "published_at": "2026-05-12T08:14:10.000Z",
  "fetched_at": "2026-07-14T16:31:03.578Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/4490",
  "original_url": "https://arxiv.org/abs/2606.12426v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}