面向智能响应生成的大语言模型（Flan-T5、LLAMA 2、DeepSeek-R1 和 ChatGPT 4）中的情感感知嵌入融合
Emotion-Aware Embedding Fusion in LLMs (Flan-T5, LLAMA 2, DeepSeek-R1, and ChatGPT 4) for Intelligent Response Generation
AI总结：
本文提出情感感知嵌入融合框架，结合多情感词典、分层融合、注意力机制及FAISS向量检索，以增强Flan-T5、LLAMA 2等大语言模型在心理治疗中生成富有同理心回应的能力。
摘要：
在自动化聊天机器人辅助的心理治疗中，富有同理心且连贯的回应至关重要。本研究旨在解决在精神病学应用中增强大语言模型（LLMs）情感与语境理解的挑战。我们提出了情感感知嵌入融合（Emotion-Aware Embedding Fusion），这是一个新颖的框架，整合了分层融合和注意力机制，以优先处理治疗记录中的语义和情感特征。我们的方法结合了多个情感词典，包括 NRC Emotion Lexicon、VADER、WordNet 和 SentiWordNet，以及最先进的大语言模型，如 Flan-T5、LLAMA 2、DeepSeek-R1 和 ChatGPT 4。包含超过 2,000 个样本的治疗会话记录使用神经网络被分割为分层级别（词、句子和会话），同时分层融合通过池化技术结合这些特征以细化情感表示。注意力机制，包括多头自注意力和交叉注意力，进一步优先处理情感和语境特征，从而能够对会话间的情感变化进行时序建模。使用 BERT、GPT-3 和 RoBERTa 计算得到的处理后嵌入存储在 Facebook AI 相似性搜索（FAISS）向量数据库中，该数据库能够在稠密向量空间中实现高效的相似性搜索和聚类。在用户查询时，相关片段被检索出来并作为上下文提供给大语言模型，增强其生成富有同理心且与语境相关回应的能力。所提出的框架在多个实际用例中进行了评估，以展示其现实世界适用性，包括 AI 驱动的治疗聊天机器人。该系统可以集成到现有的心理健康平台中，基于检索到的治疗会话数据生成个性化回应。
英文摘要：
Empathetic and coherent responses are critical in auto-mated chatbot-facilitated psychotherapy. This study addresses the challenge of enhancing the emotional and contextual understanding of large language models (LLMs) in psychiatric applications. We introduce Emotion-Aware Embedding Fusion, a novel framework integrating hierarchical fusion and attention mechanisms to prioritize semantic and emotional features in therapy transcripts. Our approach combines multiple emotion lexicons, including NRC Emotion Lexicon, VADER, WordNet, and SentiWordNet, with state-of-the-art LLMs such as Flan-T5, LLAMA 2, DeepSeek-R1, and ChatGPT 4. Therapy session transcripts, comprising over 2,000 samples are segmented into hierarchical levels (word, sentence, and session) using neural networks, while hierarchical fusion combines these features with pooling techniques to refine emotional representations. Atten-tion mechanisms, including multi-head self-attention and cross-attention, further prioritize emotional and contextual features, enabling temporal modeling of emotion-al shifts across sessions. The processed embeddings, computed using BERT, GPT-3, and RoBERTa are stored in the Facebook AI similarity search vector database, which enables efficient similarity search and clustering across dense vector spaces. Upon user queries, relevant segments are retrieved and provided as context to LLMs, enhancing their ability to generate empathetic and con-textually relevant responses. The proposed framework is evaluated across multiple practical use cases to demonstrate real-world applicability, including AI-driven therapy chatbots. The system can be integrated into existing mental health platforms to generate personalized responses based on retrieved therapy session data.
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。
