Do not Abstain! Identify and Solve the Uncertainty

TL;DR

This paper introduces ConfuseBench, a benchmark to evaluate LLMs' ability to recognize and address different sources of uncertainty, and proposes methods to improve their uncertainty handling and response quality.

Contribution

The paper presents ConfuseBench for systematic evaluation and introduces InteractDPO, a training method to enhance LLMs' capacity to identify and solve uncertainty sources.

Findings

LLMs often misattribute uncertainty to query ambiguity.

Current models struggle to identify the true source of uncertainty.

Proposed methods improve inquiry generation and uncertainty recognition.

Abstract

Despite the widespread application of Large Language Models (LLMs) across various domains, they frequently exhibit overconfidence when encountering uncertain scenarios, yet existing solutions primarily rely on evasive responses (e.g., "I don't know") overlooks the opportunity of identifying and addressing the uncertainty to generate more satisfactory responses. To systematically investigate and improve LLMs' ability of recognizing and addressing the source of uncertainty, we introduce \textbf{ConfuseBench}, a benchmark mainly focus on three types of uncertainty: document scarcity, limited capability, and query ambiguity. Experiments with ConfuseBench reveal that current LLMs struggle to accurately identify the root cause of uncertainty and solve it. They prefer to attribute uncertainty to query ambiguity while overlooking capability limitations, especially for those weaker models. To tackle this challenge, we first generate context-aware inquiries that highlight the confusing aspect of the original query. Then we judge the source of uncertainty based on the uniqueness of the inquiry's answer. Further we use an on-policy training method, InteractDPO to generate better inquiries. Experimental results demonstrate the efficacy of our approach.