{
  "id": 3868805,
  "title": "When Text Misleads: Inconsistent-Aware Reasoning for Audio-Grounded Dialogue",
  "url": "https://urgent.news/2026/08/27/when-text-misleads-inconsistent-aware-reasoning-for-audio-grounded",
  "topic": "ai",
  "section": "AI",
  "published": "2026-08-27T14:26:46.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2608.27176v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "Understanding spoken dialogue requires joint reasoning over lexical content and paralinguistic acoustic signals such as emotion and conversational intent. However, existing evaluations often allow shortcuts based on transcripts or single-modality solutions, obscuring whether models genuinely ground predictions in speech. We formalize this failure mode as cross-modal disagreement, where…",
  "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."
}