Can LLMs Learn Uncertainty on Their Own? Expressing Uncertainty Effectively in A Self-Training Manner
Shudong Liu, Zhaocong Li, Xuebo Liu, Runzhe Zhan, Derek F. Wong, Lidia S. Chao, Min Zhang
Abstract
Large language models (LLMs) often exhibit excessive, random, and uninformative uncertainty, rendering them unsuitable for decision-making in human-computer interactions. In this paper, we aim to instigate a heightened awareness of self-uncertainty in LLMs, enabling them to express uncertainty more effectively. To accomplish this, we propose an uncertainty-aware instruction tuning (UaIT) method, aligning LLMs’ perception with the probabilistic uncertainty of the generation. We conducted experiments using LLaMA2 and Mistral on multiple free-form QA tasks. Experimental results revealed a surprising 45.2% improvement in the effectiveness of uncertainty expression by LLMs, accompanied by reasonably good out-of-domain generalization capabilities. Moreover, this uncertainty expression can serve as a valuable real-time basis for human decision-making, e.g., retrieving external documents and incorporating stronger LLMs.
BibTeX
@inproceedings{liu-etal-2024-llms-learn-uncertainty,
title = "Can {LLM}s Learn Uncertainty on Their Own? Expressing Uncertainty Effectively in A Self-Training Manner",
author = "Liu, Shudong and
Li, Zhaocong and
Liu, Xuebo and
Zhan, Runzhe and
Wong, Derek F. and
Chao, Lidia S. and
Zhang, Min",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.emnlp-main.1205/",
doi = "10.18653/v1/2024.emnlp-main.1205",
pages = "21635--21645"
}