Poster
in
Workshop: Assessing World Models: Methods and Metrics for Evaluating Understanding
Are LLM Belief Updates Consistent with Bayes’ Theorem?
Sohaib Imran · Ihor Kendiukhov · Matthew Broerman · Aditya Thomas · Riccardo Campanella · Rob Lamb · Peter Atkinson
Keywords: [ Consistency checks ] [ Bayes' theorem ] [ Coherence ] [ LLMs ] [ Language Models ]
Do larger and more capable language models learn to update their "beliefs" about propositions more consistently with Bayes' theorem when presented with evidence in-context? To test this, we formulate a Bayesian Coherence Coefficient (BCC) metric and generate a dataset with which to measure the BCC. We measure BCC for multiple pre-trained-only language models across five model families, comparing against the number of model parameters, the amount of training data, and model scores on common benchmarks. Our results provide evidence for our hypothesis that larger and more capable pre-trained language models assign credences that are more coherent with Bayes' theorem. These results have important implications for our understanding and governance of LLMs.