Prism: Towards Lowering User Cognitive Load in LLMs via Complex Intent Understanding

2026-01-13

AI Summary

This work addresses the challenge that large language models (LLMs) struggle to effectively interpret users’ ambiguous and dynamically evolving intents in social platforms, often generating clarification questions that ignore logical dependencies, thereby increasing cognitive load and reducing interaction efficiency. To tackle this, the authors propose Prism, a novel framework that integrates cognitive load theory into LLM-based intent understanding for the first time. Prism comprises four key components: decomposition of complex intents, generation of logically consistent clarification questions, an intent-aware reward mechanism enhanced with Monte Carlo sampling, and a self-evolutionary fine-tuning strategy. Experimental results demonstrate that Prism reduces logical conflict rates to 11.5%, improves user satisfaction by 14.4%, and shortens task completion time by 34.8%, achieving state-of-the-art performance across multiple benchmarks.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: (Large) Language Models
• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Large language models for search

Abstract

Large Language Models are rapidly emerging as web-native interfaces to social platforms. On the social web, users frequently have ambiguous and dynamic goals, making complex intent understanding-rather than single-turn execution-the cornerstone of effective human-LLM collaboration. Existing approaches attempt to clarify user intents through sequential or parallel questioning, yet they fall short of addressing the core challenge: modeling the logical dependencies among clarification questions. Inspired by the Cognitive Load Theory, we propose Prism, a novel framework for complex intent understanding that enables logically coherent and efficient intent clarification. Prism comprises four tailored modules: a complex intent decomposition module, which decomposes user intents into smaller, well-structured elements and identifies logical dependencies among them; a logical clarification generation module, which organizes clarification questions based on these dependencies to ensure coherent, low-friction interactions; an intent-aware reward module, which evaluates the quality of clarification trajectories via an intent-aware reward function and leverages Monte Carlo Sample to simulate user-LLM interactions for large-scale,high-quality training data generation; and a self-evolved intent tuning module, which iteratively refines the LLM's logical clarification capability through data-driven feedback and optimization. Prism consistently outperforms existing approaches across clarification interactions, intent execution, and cognitive load benchmarks. It achieves stateof-the-art logical consistency, reduces logical conflicts to 11.5%, increases user satisfaction by 14.4%, and decreases task completion time by 34.8%. All data and code are released.

Problem

• complex intent understanding
• cognitive load
• logical dependencies
• intent clarification
• human-LLM collaboration

Innovation

• complex intent understanding
• cognitive load reduction
• logical dependency modeling
• clarification interaction
• self-evolved intent tuning