Skip to content
arXiv cs.CL · Papers

Lost at the End: Primacy Bias in Multimodal Retrieval-Augmented Question Answering

arXiv:2606.16494v2 Announce Type: replace Abstract: Knowledge-based visual question answering (KB-VQA) lets vision-language systems answer questions that exceed their parametric knowledge by conditioning a reader on passages retrieved from a Wikipedia-scale knowledge base. In pure-text long-context LLMs, retrieved-cont