Skip to content
arXiv cs.CL · Papers

Does AI Reviewer See the Full Picture? Attacking and Defending Multimodal Peer Review

arXiv:2606.12716v2 Announce Type: replace Abstract: The integration of Large Language Models (LLMs) and Multimodal LLMs (MLLMs) into scientific peer-review workflows introduces novel and significant risks for adversarial manipulation, especially given the multimodal nature of scientific papers where figures, not just t