{
  "id": 4770766,
  "title": "Automated Testing of LLM-Based Post Hoc Explainers Using Model Checking as an Oracle",
  "url": "https://urgent.news/2026/08/31/automated-testing-of-llm-based-post-hoc-explainers-using-model",
  "topic": "ai",
  "section": "AI",
  "published": "2026-08-31T10:54:37.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2608.30581v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "Large language models (LLMs) are used as post hoc explainers of sequential decision-making policies, producing natural-language explanations of why an action was chosen. However, LLMs often generate plausible but incorrect statements, and no existing approach systematically tests whether such explanations are faithful to the underlying environment. Two classic software testing challenges stand in…",
  "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."
}