bplaut/llm-calibration-and-correctness-prediction

This repository contains the code for our paper "Probabilities of Chat LLMs Are Miscalibrated but Still Predict Correctness on Multiple-Choice Q&A", published in Transactions on Machine Learning Research in 2025 (https://openreview.net/forum?id=E6LOh5vz5x). Correspondence to plaut@berkeley.edu.

语言：TeX · GitHub 星标：7 · Fork：0

在 GitHub 上查看原仓库