Pre-trained LLMs learn to predict HMM-generated sequences via in-context learning, approaching theoretical optimum on synthetic HMMs and matching expert models on real animal decision data.
Standardized and reproducible measurement of decision-making in mice
3 Pith papers cite this work, alongside 211 external citations. Polarity classification is still indexing.
3
Pith papers citing it
211
external citations · OpenAlex
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 3verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
Order is distinct from control, where control is defined as a local receiver-gated response law demonstrated across biological circuits and LLM response panels with reported prediction accuracies of 72-84%.
ATLAS shows constitutions induce recoverable latent geometry in LLMs that redistributes but remains detectable across models and neural perturbation data via source-defined families and AUC separations.
citing papers explorer
-
Pre-trained Large Language Models Learn Hidden Markov Models In-context
Pre-trained LLMs learn to predict HMM-generated sequences via in-context learning, approaching theoretical optimum on synthetic HMMs and matching expert models on real animal decision data.
-
Order Is Not Control
Order is distinct from control, where control is defined as a local receiver-gated response law demonstrated across biological circuits and LLM response panels with reported prediction accuracies of 72-84%.
-
ATLAS: Constitution-Conditioned Latent Geometry and Redistribution Across Language Models and Neural Perturbation Data
ATLAS shows constitutions induce recoverable latent geometry in LLMs that redistributes but remains detectable across models and neural perturbation data via source-defined families and AUC separations.