Traveling Across Languages: Benchmarking Cross-Lingual Consistency in Multimodal LLMs
This addresses the challenge of ensuring multilingual and culturally aware AI models for global applications, though it is incremental as it focuses on benchmarking rather than solving the issue.
The paper tackled the problem of inconsistent performance across languages in multimodal large language models (MLLMs) by introducing two benchmarks, KnowRecall and VisRecall, which revealed that state-of-the-art MLLMs struggle to achieve cross-lingual consistency, with evaluations in up to 15 languages.
The rapid evolution of multimodal large language models (MLLMs) has significantly enhanced their real-world applications. However, achieving consistent performance across languages, especially when integrating cultural knowledge, remains a significant challenge. To better assess this issue, we introduce two new benchmarks: KnowRecall and VisRecall, which evaluate cross-lingual consistency in MLLMs. KnowRecall is a visual question answering benchmark designed to measure factual knowledge consistency in 15 languages, focusing on cultural and historical questions about global landmarks. VisRecall assesses visual memory consistency by asking models to describe landmark appearances in 9 languages without access to images. Experimental results reveal that state-of-the-art MLLMs, including proprietary ones, still struggle to achieve cross-lingual consistency. This underscores the need for more robust approaches that produce truly multilingual and culturally aware models.