{
  "id": 2062168,
  "title": "ReWEIGH the Evidence: Calibrating Token-Level Ordinal Visual Evidence to Mitigate Hallucinations in Large Vision-Language Models",
  "url": "https://urgent.news/2026/08/19/reweigh-the-evidence-calibrating-token-level-ordinal-visual-evidence",
  "topic": "ai",
  "section": "AI",
  "published": "2026-08-19T16:23:56.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2608.19075v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "Large vision-language models (LVLMs) often hallucinate, generating content that the input image does not support. Preventing such content during decoding calls for a candidate-specific measure of how strongly the image supports the token under consideration. The model's visual-token states offer a natural source of this evidence because projecting each state through the output head reveals which…",
  "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."
}