作者位次 #3/9ACL 2026Poster· Natural Language Processing
F act V erse: A Benchmark for Factual Consistency in Interleaved Image–Text Generation
Yubo Shan · Kun Zhang · Qiming Xu · Liping Cao · Yingying Cao · Jian Zhang · Yu Wang · Jingyuan Li · Yuanzhuo Wang
摘要
Interleaved multimodal understanding and generation—where models can interactively comprehend and produce images and text in arbitrary orders—has emerged as a key research direction in generative Multimodal Large Language Models(MLLMs). Such interleaved image–text content plays an increasingly im...