Research
Vroom-Vroom at SHROOM-Visions: A Multi-Judge Committee for Detecting Hallucinated Spans in Vision-Language Outputs
arXiv:2609.17327v1 Announce Type: cross Abstract: This paper describes our submission to the SHROOM-Visions shared task on detecting and classifying hallucinated character spans in vision-language mod
arXiv:2609.17327v1 Announce Type: cross Abstract: This paper describes our submission to the SHROOM-Visions shared task on detecting and classifying hallucinated character spans in vision-language model outputs across four languages. We employ several fine-tuned vision-language models as independent annotators and combine their span predictions through character-level majority voting, and additionally explore activation probes. The approach ranks first in three of four languages and places on the podium in every language and metric. Our analysis indicates that disagreement among diverse models tracks disagreement among human annotators.
Related
- Do We Really Need External Tools to Mitigate Hallucinations? SIRA: Shared-Prefix Internal Reconstruction of Attribution
- Beyond Task Success: Behavioral and Representational Diagnostics for WAM and VLA
- VIB-Probe: Detecting and Mitigating Hallucinations in Vision-Language Models via Variational Information Bottleneck
Source: arXiv cs.AI | 2026-09-16