# MMCOMET: A Large-Scale Multimodal Commonsense Knowledge Graph for Contextual Reasoning Source: [MMCOMET: A Large-Scale Multimodal Commonsense Knowledge Graph for Contextual Reasoning]() Collection index: [llms.txt]() Data updated: 2026-03-04T05:00:12.635Z Authors: Eileen Wang, Hiba Arnaout, Dhita Pratama, Shuo Yang, Dangyang Liu, Jie Yang, Josiah Poon, Jeff Pan, Caren Han Published: 2026-03-01T11:21:50.000Z ## Abstract We present MMCOMET, the first multimodal commonsense knowledge graph (MMKG) that integrates physical, social, and eventive knowledge. MMCOMET extends the ATOMIC2020 knowledge graph to include a visual dimension, through an efficient image retrieval process, resulting in over 900K multimodal triples. This new resource addresses a major limitation of existing MMKGs in supporting complex reasoning tasks like image captioning and storytelling. Through a standard visual storytelling experiment, we show that our holistic approach enables the generation of richer, coherent, and contextually grounded stories than those produced using text-only knowledge. This resource establishes a new foundation for multimodal commonsense reasoning and narrative generation. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Multimodal Knowledge Graph Construction on Multimodal Knowledge Graphs](): Multimodal Knowledge Graph Construction; Multimodal Knowledge Graphs; Graph Size: 989. ## Original sources and implementation [Original paper]() [PDF]()