A two-stage model adding simulated-play funness to a language-model proposal prior best fits novice-invented games, but the model comparison is undermined by including the observed games in the normalization set and by in-sample weight fitting.
Using LLMs to Advance the Cognitive Science of Collectives
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
LLMs are already transforming the study of individual cognition, but their application to studying collective cognition has been underexplored. We lay out how LLMs may be able to address the complexity that has hindered the study of collectives and raise possible risks that warrant new methods.
fields
cs.HC 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Generation and Evaluation in the Human Invention Process through the Lens of Game Design
A two-stage model adding simulated-play funness to a language-model proposal prior best fits novice-invented games, but the model comparison is undermined by including the observed games in the normalization set and by in-sample weight fitting.