LLMs exhibit Bayesian-like hypothesis updating with strong-sampling bias and an evaluation-generation gap but generalize poorly outside observed data.
Knill and Alexandre Pouget
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 4verdicts
UNVERDICTED 4roles
background 1polarities
support 1representative citing papers
Information defined as maximum-caliber deviation derives IIT 3.0 cause-effect repertoires from constrained entropy maximization and equates to prediction error under CLT and LDT.
A Bayesian dynamical model reproduces time-order effects in vibrotactile discrimination experiments with few parameters, transforming stimulus space to reveal approximate perceptual symmetries absent in physical coordinates.
The adaptive bounded-rationality model anticipates hazardous takeovers with better coverage and lead time than baselines while aligning inferred parameters with eye-tracking metrics.
citing papers explorer
-
Hypothesis generation and updating in large language models
LLMs exhibit Bayesian-like hypothesis updating with strong-sampling bias and an evaluation-generation gap but generalize poorly outside observed data.
-
Information as Maximum-Caliber Deviation: A bridge between Integrated Information Theory and the Free Energy Principle
Information defined as maximum-caliber deviation derives IIT 3.0 cause-effect repertoires from constrained entropy maximization and equates to prediction error under CLT and LDT.
-
Modelling time-order effects in haptic perception with a Bayesian dynamical framework
A Bayesian dynamical model reproduces time-order effects in vibrotactile discrimination experiments with few parameters, transforming stimulus space to reveal approximate perceptual symmetries absent in physical coordinates.
-
Adaptive Bounded-Rationality Modeling of Early-Stage Takeover in Shared-Control Driving
The adaptive bounded-rationality model anticipates hazardous takeovers with better coverage and lead time than baselines while aligning inferred parameters with eye-tracking metrics.