Showing cs.CLShow all
2 papers · 1 filter
cs.CL2026
Same Evidence, Different Answer: Auditing Order Sensitivity in Multimodal Large Language Models
Akshay Paruchuri, Sanmi Koyejo, Ehsan Adeli
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 baselin…
cs.CL2026
The Cost of Language: Centroid Erasure Exposes and Exploits Modal Competition in Multimodal Language Models
Akshay Paruchuri, Ishan Chatterjee, Henry Fuchs +2
Multimodal language models systematically underperform on visual perception tasks, yet the structure underlying this failure remains poorly understood. We propose centroid replacem…