{
  "id": 17066,
  "url": "https://arxiv.org/abs/2608.06300v1",
  "title": "Bias Analysis of L2 Speaking Assessment Systems Using Concept Activation Vectors",
  "summary": "Automatic speaking assessment systems are increasingly deployed in high-stakes settings to mark second language (L2) learners' speaking tests, making it critical to show that their scores depend on speaking proficiency rather than irrelevant speaker attributes such as first language (L1) or age. Transformer-based foundation models have improved the accuracy of these L2 speaking graders, but their black-box representations make fairness and interpretability analysis more difficult. Building on pr",
  "authors": "Arya Labroo, Mengjie Qian, Kate Knill",
  "category": "research",
  "topics": "bias-fairness,safety-alignment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-08-06T17:20:58.000Z",
  "fetched_at": "2026-08-07T05:10:58.501Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/17066",
  "original_url": "https://arxiv.org/abs/2608.06300v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}