arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2601.08653cs.AI
收藏

Prism:通过复杂意图理解降低用户认知负荷

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

National Key Laboratory of Big Data and Decision(大数据与决策国家级实验室);National University of Defense Technology(国防科技大学)

Zenghua Liao, Jinzhi Liao, Xiang Zhao

AI总结:

Prism通过复杂意图理解框架降低用户认知负荷,提升交互效率与用户满意度。

摘要:

大型语言模型正迅速成为社交平台的原生界面。在社交网络中,用户经常有模糊且动态的目标,使复杂意图理解——而不是单轮执行——成为有效的人机协作的核心。现有方法试图通过顺序或并行提问来澄清用户意图,但未能解决核心挑战:建模澄清问题之间的逻辑依赖性。受认知负荷理论启发,我们提出Prism,一种新的复杂意图理解框架,能够实现逻辑一致且高效的意图澄清。Prism包含四个定制模块:复杂意图分解模块,将用户意图分解为更小、结构良好的元素并识别其中的逻辑依赖性;逻辑澄清生成模块,根据这些依赖性组织澄清问题,以确保一致、低摩擦的交互;意图感知奖励模块,通过意图感知奖励函数评估澄清轨迹的质量,并利用蒙特卡洛样本模拟用户-LLM交互以生成大规模、高质量的训练数据;以及自我演化的意图调节模块,通过数据驱动的反馈和优化迭代改进LLM的逻辑澄清能力。Prism在澄清交互、意图执行和认知负荷基准测试中均优于现有方法。它实现了最先进的逻辑一致性,将逻辑冲突减少到11.5%,将用户满意度提高14.4%,并将任务完成时间减少34.8%。所有数据和代码均已发布。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑