SycoPhantasy: Quantifying Sycophancy and Hallucination in Small Open Weight VLMs for Vision-Language Scoring of Fantasy Characters
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
Record details
Published: 27 April 2026
Source: arXiv
Category: Research
Topics: Safety & alignment · Finance, VC & PE
Retrieved: 14 July 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
Too Nice to Tell the Truth: Quantifying Agreeableness-Driven Sycophancy in Role-Playing Language Models
arXiv · 12 April 2026
Retrieval-Guided Generation for Safer Histopathology Image Captioning
arXiv · 27 April 2026
Working Memory Constraints Scaffold Learning in Transformers under Data Scarcity
arXiv · 22 April 2026
Cognitive Alignment At No Cost: Inducing Human Attention Biases For Interpretable Vision Transformers
arXiv · 21 April 2026
RefusalGuard: Geometry-Preserving Fine-Tuning for Safety in LLMs
arXiv · 3 May 2026
Reasoning Structure Matters for Safety Alignment of Reasoning Models
arXiv · 21 April 2026
How to cite this record
ethics.ai (27 April 2026), “SycoPhantasy: Quantifying Sycophancy and Hallucination in Small Open Weight VLMs for Vision-Language Scoring of Fantasy Characters,” evidence record 5317, https://ethics.ai/record/5317 (originally published by arXiv).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.