Emotion-Aware Embedding Fusion in LLMs (Flan-T5, LLAMA 2, DeepSeek-R1, and ChatGPT 4) for Intelligent Response Generation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915190366273536 |
|---|---|
| author | Rasool, Abdur Shahzad, Muhammad Irfan Aslam, Hafsa Chan, Vincent Arshad, Muhammad Ali |
| author_facet | Rasool, Abdur Shahzad, Muhammad Irfan Aslam, Hafsa Chan, Vincent Arshad, Muhammad Ali |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_01306 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Emotion-Aware Embedding Fusion in LLMs (Flan-T5, LLAMA 2, DeepSeek-R1, and ChatGPT 4) for Intelligent Response Generation Rasool, Abdur Shahzad, Muhammad Irfan Aslam, Hafsa Chan, Vincent Arshad, Muhammad Ali Computation and Language Artificial Intelligence Computers and Society 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. |
| title | Emotion-Aware Embedding Fusion in LLMs (Flan-T5, LLAMA 2, DeepSeek-R1, and ChatGPT 4) for Intelligent Response Generation |
| topic | Computation and Language Artificial Intelligence Computers and Society |
| url | https://arxiv.org/abs/2410.01306 |