MMSEARCH: Benchmarking the Potential of Large Models as Multi-Modal Search Engines
Topics: AI (Deep Learning), AIOverviews, LLMO, Ranking, Reranking
The document “MMSEARCH: Benchmarking the Potential of Large Models as Multi-Modal Search Engines” explores the capabilities of Large Language Models (LLMs) and Large Multimodal Models (LMMs) in enhancing AI search engines for multimodal search tasks. The key focus is on developing and evaluating MMSEARCH-ENGINE, a multimodal search pipeline that integrates textual and visual content, and MMSEARCH, a benchmarking dataset for assessing LMMs on multimodal search queries.