This work introduces a unified framework for composing multiple LMs into ensemble distributions parameterized by a broad family of aggregation functions, and introduces an SMC algorithm that operates in a shared byte space, enabling ensembles of models with mismatching vocabularies and consistent sampling in the limit.
R. Chan, Tianyu Liu, Samuel Kiegeland et al.· arXiv.org· 3 citations
An importance sampling estimator is introduced that approximates the probability of an abstract unit by marginalizing over realizations generated by a text-to-speech model, and finds that surprisal values for sub-lexical units are predictive of pupil dilation.
Z. Hopton, Samuel Kiegeland, F. Re et al.· 0 citations
This work operationalizes the Monte Carlo estimator of unigram surprisal from a language model, along with a marginalized variant that has lower variance empirically, and confirms prior findings that frequency can be a stronger predictor of processing effort than contextual surprisal under this unified framework.
Z. Hopton, F. Re, Samuel Kiegeland et al.· Proceedings of the 2026 Conf...· 1 citation
CogGym is introduced, a scalable, unified framework grounded in cognitive science for systematically comparing model and human behavior on matched experimental trials, and intends for CogGym to provide a living evaluation framework that continually incorporates new cognitive science experiments to characterize where mo...
Lance Ying, Jin-Zhou Wu, Y. Wang et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.