2025/03/07 by Ilinykh, Nikolai, Lappin, Shalom, Sayeed, Asad +1
#Computation and Language (cs.CL) #FOS: Computer and information sciences
paper · doi:10.48550/arxiv.2503.05298
We demonstrate that large multimodal language models differ substantially from humans in the distribution of coreferential expressions in a visual storytelling task. We introduce a number of metrics to quantify the characteristics of coreferential patterns in both human- and machine-written texts. Humans distribute coreferential expressions in a way that maintains consistency across texts and images, interleaving references to different entities in a highly varied way. Machines are less able to track mixed references, despite achieving perceived improvements in generation quality. Materials, metrics, and code for our study are available at https://github.com/GU-CLASP/coreference-context-scope.