Finetuning Language Models to Emit Linguistic Expressions of Uncertainty

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chaudhry, Arslan, Thiagarajan, Sridhar, Gorur, Dilan
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929504264388608
author Chaudhry, Arslan
Thiagarajan, Sridhar
Gorur, Dilan
author_facet Chaudhry, Arslan
Thiagarajan, Sridhar
Gorur, Dilan
contents Large language models (LLMs) are increasingly employed in information-seeking and decision-making tasks. Despite their broad utility, LLMs tend to generate information that conflicts with real-world facts, and their persuasive style can make these inaccuracies appear confident and convincing. As a result, end-users struggle to consistently align the confidence expressed by LLMs with the accuracy of their predictions, often leading to either blind trust in all outputs or a complete disregard for their reliability. In this work, we explore supervised finetuning on uncertainty-augmented predictions as a method to develop models that produce linguistic expressions of uncertainty. Specifically, we measure the calibration of pre-trained models and then fine-tune language models to generate calibrated linguistic expressions of uncertainty. Through experiments on various question-answering datasets, we demonstrate that LLMs are well-calibrated in assessing their predictions, and supervised finetuning based on the model's own confidence leads to well-calibrated expressions of uncertainty, particularly for single-claim answers.
format Preprint
id arxiv_https___arxiv_org_abs_2409_12180
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Finetuning Language Models to Emit Linguistic Expressions of Uncertainty
Chaudhry, Arslan
Thiagarajan, Sridhar
Gorur, Dilan
Computation and Language
Machine Learning
Large language models (LLMs) are increasingly employed in information-seeking and decision-making tasks. Despite their broad utility, LLMs tend to generate information that conflicts with real-world facts, and their persuasive style can make these inaccuracies appear confident and convincing. As a result, end-users struggle to consistently align the confidence expressed by LLMs with the accuracy of their predictions, often leading to either blind trust in all outputs or a complete disregard for their reliability. In this work, we explore supervised finetuning on uncertainty-augmented predictions as a method to develop models that produce linguistic expressions of uncertainty. Specifically, we measure the calibration of pre-trained models and then fine-tune language models to generate calibrated linguistic expressions of uncertainty. Through experiments on various question-answering datasets, we demonstrate that LLMs are well-calibrated in assessing their predictions, and supervised finetuning based on the model's own confidence leads to well-calibrated expressions of uncertainty, particularly for single-claim answers.
title Finetuning Language Models to Emit Linguistic Expressions of Uncertainty
topic Computation and Language
Machine Learning
url https://arxiv.org/abs/2409.12180