Hugging Face Trending Papers

Same Evidence, Different Answer: Auditing Order Sensitivity in Multimodal Large Language Models

Read the original on Hugging Face Trending Papers →

Standard benchmarks for multimodal large language models (MLLMs) score each item on one canonical ordering and miss whether order-irrelevant shuffling changes the answer, a baseline reliability property called for by emerging AI evaluation guidelines. We introduce Facet-Probe, a five-facet audit (option, evidence-chunk, document-rank, image-set, and mixed-modality ordering) of 18 frontier and open-weight MLLMs.

Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.

arXiv Machine Learning
Jun 25

Same Evidence, Different Answer: Auditing Order Sensitivity in Multimodal Large Language Models

arXiv:2606. 26079v1 Announce Type: cross Abstract: Standard benchmarks for multimodal large language models (MLLMs) score each item on one canonical ordering and miss whether order-irrelevant shuffling changes the answer, a baseline reliability property called for by emerging AI evaluation guidelines.

By Akshay Paruchuri, Sanmi Koyejo, Ehsan Adeli