{
  "id": 5317,
  "url": "https://arxiv.org/abs/2604.24346v1",
  "title": "SycoPhantasy: Quantifying Sycophancy and Hallucination in Small Open Weight VLMs for Vision-Language Scoring of Fantasy Characters",
  "summary": "Vision-language models (VLMs) are increasingly deployed as evaluators in tasks requiring nuanced image understanding, yet their reliability in scoring alignment between images and text descriptions remains underexplored. We investigate whether small, open-weight VLMs exhibit \\emph{sycophantic} behavior when evaluating image-text alignment: assigning high scores without grounding their judgments in visual evidence. To quantify this phenomenon, we introduce the \\emph{Bluffing Coefficient} (\\bc), a",
  "authors": "Arya Shah, Deepali Mishra, Chaklam Silpasuwanchai",
  "category": "research",
  "topics": "safety-alignment,finance-investment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-04-27T11:39:18.000Z",
  "fetched_at": "2026-07-14T16:31:40.220Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/5317",
  "original_url": "https://arxiv.org/abs/2604.24346v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}