{
  "id": 19159,
  "url": "https://arxiv.org/abs/2608.13484v1",
  "title": "Toward a Gricean Retreat: Probing LLMs for Knowledge Boundaries and Referent Specificity",
  "summary": "When asked about entities outside their knowledge boundary, LLMs routinely fabricate plausible-sounding details rather than backing off to safer, more general claims. We frame this failure through a Gricean lens: a cooperative speaker who is uncertain about a referent retreats up the specificity hierarchy, trading informativeness for truthfulness. We ask whether LLMs have the ingredients to perform this retreat. Using a T-REx-based benchmark that varies entity familiarity and referent specificit",
  "authors": "Dananjay Srinivas, Saksham Khatwani, Maria Pacheco",
  "category": "research",
  "topics": null,
  "orgs": null,
  "regions": null,
  "published_at": "2026-08-13T17:13:41.000Z",
  "fetched_at": "2026-08-14T05:10:49.168Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/19159",
  "original_url": "https://arxiv.org/abs/2608.13484v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}