作者位次 #4/8ACL 2026Findings· Findings of ACL
OMHB ench: Benchmarking Balanced and Grounded Omni-Modal Multi-Hop Reasoning
Seunghee Kim · Ingyu Bang · Seokgyu Jang · Changhyeon Kim · Sanghwan Bae · Jihun Choi · richeng xuan · Taeuk Kim
摘要
Multimodal Large Language Models (MLLMs) have increasingly supported omni-modal processing across text, vision, and speech. However, existing evaluation frameworks for such models suffer from critical limitations, including modality shortcuts and biased reasoning paths. To address these challenge...