Vroom-Vroom at SHROOM-Visions: A Multi-Judge Committee for Detecting Hallucinated Spans in Vision-Language Outputs
This paper uses several fine-tuned vision-language models as independent annotators and combines their span predictions through character-level majority voting, and additionally explores activation probes to indicate that disagreement among diverse models tracks disagreement among human annotators.
Toqeer Ehsan, Nico Penttilä, Richard Schmidt et al.
· 1 citation