5 papers
Can Humans Dream of Electric Sheep? Human-Written Samples for Fine-Grained Vision-and-Language Hallucination Benchmarking
Timothee Mickus, Claudio Savelli, Eduardo Calò +10
In an age of rapid model turnover, how do we make hallucination evaluation more perennial? We explore whether human-written hallucination samples could take the place of model-gene…
Pathways of Visual Information Flow in Vision-Language Models
Israfel Salazar, Stella Frank, Dan Oneata +2
We study how visual information is routed in vision-language models (VLMs). Using causal patching on controlled synthetic and natural datasets, we find that models rely on two dist…
EvalCards: A Framework for Standardized Evaluation Reporting
Ruchira Dhar, Danae Sanchez Villegas, Antonia Karamolegkou +11
Evaluation has long been a central concern in NLP, and transparent reporting practices are more critical than ever in today's landscape of rapidly released open-access models. Draw…
Movie Facts and Fibs (MF): A Benchmark for Long Movie Understanding
Emmanouil Zaranis, António Farinhas, Saul Santos +28
Despite recent progress in vision-language models (VLMs), holistic understanding of long-form video content remains a significant challenge, partly due to limitations in current be…
Seeing What Tastes Good: Revisiting Multimodal Distributional Semantics in the Billion Parameter Era
Dan Oneata, Desmond Elliott, Stella Frank
Human learning and conceptual representation is grounded in sensorimotor experience, in contrast to state-of-the-art foundation models. In this paper, we investigate how well such…