{
  "id": 4777356,
  "title": "BLOOM-WILT: Logit Tilting for Behaviour Elicitation in Automated LLM Auditing",
  "url": "https://urgent.news/2026/08/31/bloom-wilt-logit-tilting-for-behaviour-elicitation-in-automated-llm",
  "topic": "ai",
  "section": "AI",
  "published": "2026-08-31T17:10:59.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2608.31105v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "Users of a deployed language model routinely encounter behaviours that testing almost never surfaces, since deployment puts the model through orders of magnitude more interactions than any evaluation can simulate. Automated auditors make testing cheap to scale and flexible enough to cover almost any specified behaviour, yet their lack of optimisation pressure makes them sample-inefficient. To…",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}