Better autoregressive regression with LLMs via regression-aware fine-tuning

Large language models (LLMs) have shown strong results on a range of applications, including regression and scoring tasks. Typically, one obtains outputs from an LLM via autoregressive sampling from the model's output distribution. We show that this inference strategy can be sub-optimal for common regression and scoring evaluation metrics. As a remedy, we build on prior work on Minimum Bayes Risk decoding, and propose alternate inference strategies that estimate the Bayes-optimal solution for regression and scoring metrics in closed-form from sampled responses. We show that our proposal significantly improves over baselines across datasets and models. p(y|x) LLM y 1 y 2 y 3 y 4 y 5 sampling from p(y|x) forward pass What is the rating corresponding to the following review on the scale of 1 to 5? Review: this product is great! Rating: Decision rule