LLMs exhibit Bayesian-like hypothesis updating with strong-sampling bias and an evaluation-generation gap but generalize poorly outside observed data.
-D., Blankertz, B., and Bießmann, F
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
The CPA-PA metric approximates ground-truth neural activity via CCA alignment and participant averaging, yielding 300-1000% better single-participant evaluations than conventional scores on synthetic and real MEEG data.
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.
-
Robust Evaluation of Neural Encoding Models via ground-truth approximation
The CPA-PA metric approximates ground-truth neural activity via CCA alignment and participant averaging, yielding 300-1000% better single-participant evaluations than conventional scores on synthetic and real MEEG data.