Skip to content

Latest commit

 

History

History
66 lines (66 loc) · 2.54 KB

2024-09-10-giovannotti24a.md

File metadata and controls

66 lines (66 loc) · 2.54 KB
title booktitle year volume series month publisher pdf url abstract layout issn id tex_title firstpage lastpage page order cycles bibtex_editor editor bibtex_author author date address container-title genre issued extras
Calibrated Large Language Models for Binary Question Answering
Proceedings of the Thirteenth Symposium on Conformal and Probabilistic Prediction with Applications
2024
230
Proceedings of Machine Learning Research
0
PMLR
Quantifying the uncertainty of predictions made by large language models (LLMs) in binary text classification tasks remains a challenge. Calibration, in the context of LLMs, refers to the alignment between the model’s predicted probabilities and the actual correctness of its predictions. A well-calibrated model should produce probabilities that accurately reflect the likelihood of its predictions being correct. We propose a novel approach that utilizes the inductive Venn–Abers predictor (IVAP) to calibrate the probabilities associated with the output tokens corresponding to the binary labels. Our experiments on the BoolQ dataset using the Llama 2 model demonstrate that IVAP consistently outperforms the commonly used temperature scaling method for various label token choices, achieving well-calibrated probabilities while maintaining high predictive quality. Our findings contribute to the understanding of calibration techniques for LLMs and provide a practical solution for obtaining reliable uncertainty estimates in binary question answering tasks, enhancing the interpretability and trustworthiness of LLM predictions.
inproceedings
2640-3498
giovannotti24a
Calibrated Large Language Models for Binary Question Answering
218
235
218-235
218
false
Vantini, Simone and Fontana, Matteo and Solari, Aldo and Bostr\"{o}m, Henrik and Carlsson, Lars
given family
Simone
Vantini
given family
Matteo
Fontana
given family
Aldo
Solari
given family
Henrik
Boström
given family
Lars
Carlsson
Giovannotti, Patrizio and Gammerman, Alexander
given family
Patrizio
Giovannotti
given family
Alexander
Gammerman
2024-09-10
Proceedings of the Thirteenth Symposium on Conformal and Probabilistic Prediction with Applications
inproceedings
date-parts
2024
9
10