Aura：大型语言模型响应的轮内动态情感感知适配
Aura: Dynamic Intra-Turn Emotion-Aware Adaptation of Large Language Model Responses
浏览论文内容
中文总结 AI 辅助
本文提出Aura框架，通过感知用户情绪、概率信念模型选干预、LoRA适配器定制响应，经20人用户研究，较Llama-3提升学习增益、减21%交互时间，优化人机交互。
中文摘要 AI 辅助
有效的人机交互需要能够动态适应用户行为与认知变化的系统。用户与大型语言模型（LLM）交互时，这些模型通常仅针对提示词做出响应，无法感知用户的即时反应，这种沟通同步性的缺失可能会导致实时信息过载或困惑未解决。本文提出Aura框架，该框架使LLM系统能够根据用户的情绪变化动态调整输出：Aura的感知模块通过面部表情持续估计用户的情绪状态；策略模块通过概率信念模型选择干预措施；生成模块使用参数高效的低秩适配（LoRA）适配器，在响应生成的轮中生成符合上下文的定制化响应。我们在信息查询任务中开展了被试内用户研究（N=20），评估Aura的性能，结果显示，与Llama-3基线相比，Aura实现了统计学上显著更高的归一化感知学习增益，且相较于现有LLM基线（GPT-4o、Llama-3），交互时间减少了21%。我们的结果表明，实时、上下文敏感的干预措施可在不显著降低事实准确性的情况下提升学习效率与用户满意度，Aura为构建更具响应性和有效性的人机交互提供了可能。
英文摘要
Effective human-AI interaction requires systems that dynamically adapt to a user's behavior and evolving understanding. When users interact with Large Language Models (LLMs), these models typically respond to prompts without sensing the user's immediate reactions. This lack of communicative synchrony can lead to information overload or leave confusion unresolved in real time. In this paper, we introduce Aura, a framework that enables LLM systems to dynamically modulate output based on a user's evolving emotions. Aura's Perception Module continuously estimates the user's emotional state from facial expressions. Our Policy Module then selects interventions through a probabilistic belief model. Finally, Aura's Generation Module uses parameter-efficient Low-Rank Adaptation (LoRA) adapters to produce contextually tailored responses mid-turn during response generation. We evaluated Aura in a within-subjects user study (N=20) on information-seeking tasks, where it achieved statistically significantly higher normalized perceived learning gains than a Llama-3 baseline and reduced interaction time by 21% relative to existing LLM baselines (GPT-4o, Llama-3). Our results indicate that real-time, context-sensitive interventions can improve learning efficiency and user satisfaction without observable degradation in factual accuracy. Aura thus supports the potential for more responsive and effective human-AI interaction.
