U-Lens: Supporting User Uncertainty Management in Long-Form LLM Responses

2026-07-12

AI Summary

This work addresses the challenge that long-form texts generated by large language models often contain distributed uncertainty, which users struggle to identify, assess, and act upon effectively. To tackle this issue, the authors propose U-Lens, a system grounded in user research that articulates a three-stage user need—interpretation, evaluation, and decision-making—and shifts uncertainty support from isolated confidence indicators toward user-centered, end-to-end management. Guided by stage-specific and cross-stage design principles, U-Lens integrates human-computer interaction design, contextual goal organization, priority-aware ranking algorithms, and interactive visualization to structurally surface uncertain content, offer explanatory context, and guide responsive actions. User studies demonstrate that, compared to conventional approaches, U-Lens significantly improves verification efficiency, optimizes cognitive resource allocation, reduces subjective workload, and enhances perceived support across all stages.

Abstract

Large language models (LLMs) are increasingly used to generate long-form answers for knowledge-intensive tasks, but users often struggle to decide which parts of a response deserve scrutiny, why they may be unreliable, and what to do next. Prior work on uncertainty communication has largely focused on making uncertainty visible through cues such as confidence scores, leaving less support for the broader process of managing uncertainty distributed across a long response. Through a formative study, we examine how users manage such uncertainty across three stages: interpretation, evaluation, and decision. Based on these insights, we derive design guidelines that address both stage-specific and cross-stage needs: uncertainty target representation, evaluative explanation, response guidance, and interactive presentation. We instantiate these guidelines in U-Lens, an uncertainty-management support system that organizes uncertain information in long-form responses into contextual inspection targets, prioritizes them for attention, and connects each target with evaluative context and response options. We evaluated U-Lens in a controlled within-subjects study with 18 participants, comparing it against a confidence-cue baseline. Our results show that U-Lens improved verification efficiency and effort allocation, lowered perceived workload, and strengthened perceived support across interpretation, evaluation, and decision stages. This work reframes uncertainty support for generative AI from presenting isolated, text-centered cues toward supporting the user-centered process of interpreting, evaluating, and acting on uncertain information.

Problem

• uncertainty management
• long-form LLM responses
• user decision-making
• interpretation
• evaluation

Innovation

• uncertainty management
• long-form LLM responses
• user-centered design
• interactive explanation
• confidence cues