{
  "id": 4596,
  "url": "https://arxiv.org/abs/2605.09922v1",
  "title": "Team-Based Self-Play With Dual Adaptive Weighting for Fine-Tuning LLMs",
  "summary": "While recent self-training approaches have reduced reliance on human-labeled data for aligning LLMs, they still face critical limitations: (i) sensitivity to synthetic data quality, leading to instability and bias amplification in iterative training; (ii) ineffective optimization due to a diminishing gap between positive and negative responses over successive training iterations. In this paper, we propose Team-based self-Play with dual Adaptive Weighting (TPAW), a novel self-play algorithm desig",
  "authors": "Wu Li, Yigeng Zhou, Zesheng Shi, Yequan Wang, Min Zhang, Jing Li",
  "category": "research",
  "topics": "bias-fairness",
  "orgs": null,
  "regions": null,
  "published_at": "2026-05-11T03:17:31.000Z",
  "fetched_at": "2026-07-14T16:31:08.354Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/4596",
  "original_url": "https://arxiv.org/abs/2605.09922v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}