Knowledge of Knowledge: Exploring Known-Unknowns Uncertainty with Large Language Models

by   Alfonso Amayuelas, et al.
City of Waterloo
The Regents of the University of California

This paper investigates the capabilities of Large Language Models (LLMs) in the context of understanding their own knowledge and measuring their uncertainty. We argue this is an important feature for mitigating hallucinations. Specifically, we focus on addressing known-unknown questions, characterized by high uncertainty due to the absence of definitive answers. To facilitate our study, we collect a dataset with new Known-Unknown Questions (KUQ) and propose a novel categorization scheme to elucidate the sources of uncertainty. Subsequently, we assess the LLMs' ability to differentiate between known and unknown questions and classify them accordingly. Moreover, we evaluate the quality of their answers in an Open-Ended QA setting. To quantify the uncertainty expressed in the answers, we create a semantic evaluation method that measures the model's accuracy in expressing uncertainty between known vs unknown questions.


page 1

page 2

page 3

page 4


ExpertQA: Expert-Curated Questions and Attributed Answers

As language models are adapted by a more sophisticated and diverse set o...

Teaching language models to support answers with verified quotes

Recent large language models often answer factual questions correctly. B...

TellMeWhy: A Dataset for Answering Why-Questions in Narratives

Answering questions about why characters perform certain actions is cent...

Chain-of-Verification Reduces Hallucination in Large Language Models

Generation of plausible yet incorrect factual information, termed halluc...

Who's the Best Detective? LLMs vs. MLs in Detecting Incoherent Fourth Grade Math Answers

Written answers to open-ended questions can have a higher long-term effe...

Do Large Language Models Know What They Don't Know?

Large language models (LLMs) have a wealth of knowledge that allows them...

Enhancing QA Systems with Complex Temporal Question Processing Capabilities

This paper presents a multilayered architecture that enhances the capabi...

Please sign up or login with your details

Forgot password? Click here to reset