Position: Uncertainty Quantification Needs Reassessment for Large-language Model Agents

TL;DR

This paper argues that traditional uncertainty measures are insufficient for large-language model agents in interactive settings and proposes new research directions to better quantify and communicate uncertainties in human-AI interactions.

Contribution

It introduces three novel uncertainty research directions—underspecification, interactive learning, and output uncertainties—for LLM agents in open, interactive environments.

Findings

Traditional uncertainty definitions conflict in interactive LLM settings

Proposes three new uncertainty research directions for LLM agents

Aims to improve transparency and trust in human-AI interactions

Abstract

Large-language models (LLMs) and chatbot agents are known to provide wrong outputs at times, and it was recently found that this can never be fully prevented. Hence, uncertainty quantification plays a crucial role, aiming to quantify the level of ambiguity in either one overall number or two numbers for aleatoric and epistemic uncertainty. This position paper argues that this traditional dichotomy of uncertainties is too limited for the open and interactive setup that LLM agents operate in when communicating with a user, and that we need to research avenues that enrich uncertainties in this novel scenario. We review the literature and find that popular definitions of aleatoric and epistemic uncertainties directly contradict each other and lose their meaning in interactive LLM agent settings. Hence, we propose three novel research directions that focus on uncertainties in such human-computer interactions: Underspecification uncertainties, for when users do not provide all information or define the exact task at the first go, interactive learning, to ask follow-up questions and reduce the uncertainty about the current context, and output uncertainties, to utilize the rich language and speech space to express uncertainties as more than mere numbers. We expect that these new ways of dealing with and communicating uncertainties will lead to LLM agent interactions that are more transparent, trustworthy, and intuitive.