{
  "id": 18844,
  "url": "https://link.springer.com/article/10.1007/s00146-026-03292-3",
  "title": "Self-referential consistency in stateless language models: a behavioral perspective",
  "summary": "Large language models (LLMs) increasingly generate outputs that resemble introspection, including self-reference, epistemic modulation, and claims about their internal states. This study investigates whether such behaviors reflect stable underlying patterns or merely surface-level generative artifacts. We evaluated five open-weight, stateless LLMs using a structured battery of 21 introspective prompts. The main corpus comprised 1050 completions collected under a baseline decoding condition ( tem",
  "authors": null,
  "category": "research",
  "topics": "finance-investment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-08-12T00:00:00.000Z",
  "fetched_at": "2026-08-13T05:10:37.786Z",
  "source_slug": "x-ai-society",
  "source_name": "AI & Society",
  "source_homepage": "https://link.springer.com/journal/146",
  "ethics_ai_record_url": "https://ethics.ai/record/18844",
  "original_url": "https://link.springer.com/article/10.1007/s00146-026-03292-3",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}