MUCAR: Benchmarking Multilingual Cross-Modal Ambiguity Resolution for Multimodal Large Language Models
This addresses the problem of improving ambiguity comprehension in multimodal AI systems for researchers and developers, though it is incremental as it focuses on benchmarking rather than proposing a new method.
The authors tackled the challenge of resolving ambiguities in multimodal contexts by introducing MUCAR, a benchmark for evaluating multilingual cross-modal ambiguity resolution in multimodal large language models, revealing that 19 state-of-the-art models show substantial performance gaps compared to humans.
Multimodal Large Language Models (MLLMs) have demonstrated significant advances across numerous vision-language tasks. MLLMs have shown promising capability in aligning visual and textual modalities, allowing them to process image-text pairs with clear and explicit meanings. However, resolving the inherent ambiguities present in real-world language and visual contexts remains a challenge. Existing multimodal benchmarks typically overlook linguistic and visual ambiguities, relying mainly on unimodal context for disambiguation and thus failing to exploit the mutual clarification potential between modalities. To bridge this gap, we introduce MUCAR, a novel and challenging benchmark designed explicitly for evaluating multimodal ambiguity resolution across multilingual and cross-modal scenarios. MUCAR includes first a multilingual dataset where ambiguous textual expressions are uniquely resolved by corresponding visual contexts, and second a dual-ambiguity dataset that systematically pairs ambiguous images with ambiguous textual contexts, with each combination carefully constructed to yield a single, clear interpretation through mutual disambiguation. Extensive evaluations involving 19 state-of-the-art multimodal models--encompassing both open-source and proprietary architectures--reveal substantial gaps compared to human-level performance, highlighting the need for future research into more sophisticated cross-modal ambiguity comprehension methods, further pushing the boundaries of multimodal reasoning.