Fig. 3: Supervised fine-tuning teaches LLMs to approximate probabilistic inference.
From: Bayesian teaching enables probabilistic reasoning in large language models
We show accuracy after the first round and the final (fifth) round across different assistants. We compare the original LLMs, LLMs fine-tuned on user interactions with the Bayesian Assistant, and LLMs fine-tuned on user interactions with an oracle, which always provides the correct answer. Both types of fine-tuning significantly improve LLMs’ performance, and Bayesian teaching is consistently more effectively than oracle teaching. Error bars show the standard error across three random seeds (and three training runs). All results are statistically significant, p < 0.001 (see Supplementary Section F).
