{
  "id": 18805,
  "url": "https://arxiv.org/abs/2608.11493v1",
  "title": "From Prompting to Behavioral Alignment: Personalized LLM Judges for Recommendation Evaluation",
  "summary": "Traditional offline recommendation evaluation relies heavily on complex, manually maintained feature pipelines that are difficult to scale. While Large Language Models (LLMs) offer a promising alternative by predicting user engagement directly from raw text logs, empirical analysis in this study identifies a critical failure mode termed bidirectional rationalization. In a zero-shot setting, LLMs are found to convincingly argue for both positive and negative user engagement outcomes on the exact",
  "authors": "Alireza S. Ziabari, Kat Ellis, Colleen Chan, Ding Tong",
  "category": "research",
  "topics": "safety-alignment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-08-11T23:06:39.000Z",
  "fetched_at": "2026-08-13T05:10:37.786Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/18805",
  "original_url": "https://arxiv.org/abs/2608.11493v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}