{
  "id": 7576,
  "url": "https://arxiv.org/abs/2603.06874v1",
  "title": "LieCraft: A Multi-Agent Framework for Evaluating Deceptive Capabilities in Language Models",
  "summary": "Large Language Models (LLMs) exhibit impressive general-purpose capabilities but also introduce serious safety risks, particularly the potential for deception as models acquire increased agency and human oversight diminishes. In this work, we present LieCraft: a novel evaluation framework and sandbox for measuring LLM deception that addresses key limitations of prior game-based evaluations. At its core, LieCraft is a novel multiplayer hidden-role game in which players select an ethical alignment",
  "authors": "Matthew Lyle Olson, Neale Ratzlaff, Musashi Hinck, Tri Nguyen, Vasudev Lal, Joseph Campbell et al.",
  "category": "research",
  "topics": "safety-alignment,agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-03-06T20:49:48.000Z",
  "fetched_at": "2026-07-14T16:33:21.047Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/7576",
  "original_url": "https://arxiv.org/abs/2603.06874v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}