{
  "id": 14049,
  "url": "https://arxiv.org/abs/2607.24435v1",
  "title": "LEX-EC: A Lexical Evidence-Channel Audit Framework for Zero-Shot LLM Personality Classification in Black-Box Settings",
  "summary": "Large language models may easily assign personality labels from text, but model interpretability remains an open problem. To address this gap, we introduce LEX-EC, a reusable black-box audit framework combining prevalence and agreement diagnostics with controlled lexical ablation to distinguish marginal-distribution effects from trait-associated signal recoverable under restricted evidence. Using this framework, we illustrate how various text genres may exhibit sharply different profiles: free-f",
  "authors": "Brittany Harbison, Ashok K. Goel",
  "category": "research",
  "topics": "safety-alignment,healthcare,transparency",
  "orgs": null,
  "regions": null,
  "published_at": "2026-07-27T13:45:12.000Z",
  "fetched_at": "2026-07-28T05:10:12.325Z",
  "source_slug": "x-arxiv-cs-ai",
  "source_name": "arXiv cs.AI",
  "source_homepage": "https://arxiv.org/list/cs.AI/recent",
  "ethics_ai_record_url": "https://ethics.ai/record/14049",
  "original_url": "https://arxiv.org/abs/2607.24435v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}