Vision-language (VL) models are typically built by fine-tuning a language model to attend to visual features in service of a Visual Question-Answering objective. We ask whether this alignment changes how language models represent text---especially on tasks where visualization would help, like geometry questions posed i...
Language models (LMs) are increasingly used for tasks that require reasoning about hidden variables from a few observations, for which Bayesian inference is the normatively correct solution. While supervised fine-tuning of an LM on the outputs of an optimal $\textit{Bayesian}$ model leads to near-Bayesian behavior, sta...
Polina Tsvilodub, Andreas Waldis, Lin-Lu Qiu et al.· 0 citations
The results indicate that any immediate effects on opinions of AI are modest, although they leave open the possibility that anthropomorphic language could have an effect in naturalistic settings, or over gradual, continued exposure.
Betty Li Hou, Sophie Hao, Sunoo Park et al.· 0 citations
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.· 0 citations
This work introduces a controlled setting to study the causes and training dynamics of cross-lingual knowledge transfer by training small Transformer models from scratch on synthetic multilingual datasets and suggests methods to encourage representational unification as part of training that would improve LLMs'cross-li...
C. Blum, Katja Filipova, Ann Yuan et al.· arXiv.org· 5 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
