CLAIM: Leading Open-domain Active Clarification of Large Language Models with Uncertainty Measurement

2026-08-12

AI Summary

This work addresses the challenge of ineffective clarification in open-domain human–AI interaction, where large language models often struggle with ambiguous or incomplete user queries, and existing approaches rely on costly human annotations. To overcome this limitation, the authors propose CLAIM, a novel framework that introduces an uncertainty-driven active clarification learning mechanism. CLAIM quantifies query uncertainty through the entropy of responses from multiple models, automatically generates high-quality synthetic data, and trains a unified clarification decision model via semantic clustering, supervised fine-tuning (SFT), and group relative policy optimization (GRPO). Notably, the method requires no human preference labels and achieves substantial improvements in proactive understanding capability under zero manual data conditions, enabling a low-cost, highly generalizable clarification strategy for open-domain settings.

Abstract

In open-domain human-computer interaction scenarios, large language models (LLMs) frequently encounter user queries that are ambiguous or incomplete. In such cases, directly producing an answer often leads to overgeneralized, erroneous, or low-information responses. In contrast, asking clarifying questions can substantially improve interaction quality. However, existing approaches still rely heavily on manually annotated data or preference alignment to address two fundamental challenges: when clarification is necessary, and which aspect of the query should be clarified. This reliance incurs high annotation costs and limits generalization. To address these challenges, we propose CLAIM, an uncertainty-driven framework for active clarification learning in open-domain settings. CLAIM eliminates the need for explicit human preference annotations by quantifying query uncertainty through the entropy induced by answer disagreements across multiple models. This uncertainty signal is then used to construct high-quality synthetic data, enabling the training of a unified clarification decision model through a combination of supervised learning and reinforcement learning. Specifically, we propose an entropy-driven synthetic data generation pipeline that integrates entropy-based uncertainty estimation with semantic clustering and reasoning-based judgments, enabling reliable automatic annotation of clarification requirements. To train CLAIM, we formulate the clarification process as a structured decision generation problem and adopt a training paradigm that combines supervised fine-tuning (SFT) with group-relative policy optimization (GRPO). Experimental results demonstrate that CLAIM can learn stable and generalizable clarification strategies without relying on manually labeled data, offering a low-cost and robust solution for proactive understanding in real-world open-domain interactions with LLMs.

Problem

• open-domain interaction
• active clarification
• uncertainty measurement
• large language models
• ambiguous queries

Innovation

• uncertainty measurement
• active clarification
• synthetic data generation
• entropy-driven learning
• reinforcement learning