NEWS · RESEARCH · #240
LLMs Are Not (Consistently) Bayesian — paper quantifies deviations from Bayes updates
The paper treats LLMs as information-processing rules and introduces the 'information processing gap' metric to quantify deviations from Bayesian updates when LLMs update probabilistic beliefs in light of new evidence. The authors run extensive experiments to evaluate internal (in)consistencies of LLMs' belief-updating behavior, with relevance to high-stakes domains like medicine, science and law.
KEY POINTS
- The paper treats LLMs as information-processing rules and introduces the 'information processing gap' metric to quantify deviations from Bayesian updates when LLMs update probabilistic beliefs in light of new evidence.
- The authors run extensive experiments to evaluate internal (in)consistencies of LLMs' belief-updating behavior, with relevance to high-stakes domains like medicine, science and law.
- Quantifying when and how LLMs diverge from Bayesian belief-updating matters because such divergences can affect reliability and decision-making in uncertainty-sensitive, high-stakes applications.
WHY IT MATTERS
Quantifying when and how LLMs diverge from Bayesian belief-updating matters because such divergences can affect reliability and decision-making in uncertainty-sensitive, high-stakes applications.