Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2410.16385 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910660015685632 |
|---|---|
| author | Kumar, Sahil Paikar, Deepa Vutukuri, Kiran Sai Ali, Haider Ainala, Shashidhar Reddy Krishnan, Aditya Murli Zhang, Youshan |
| author_facet | Kumar, Sahil Paikar, Deepa Vutukuri, Kiran Sai Ali, Haider Ainala, Shashidhar Reddy Krishnan, Aditya Murli Zhang, Youshan |
| contents | Effective communication within universities is crucial for addressing the diverse information needs of students, alumni, and external stakeholders. However, existing chatbot systems often fail to deliver accurate, context-specific responses, resulting in poor user experiences. In this paper, we present KatzBot, an innovative chatbot powered by KatzGPT, a custom Large Language Model (LLM) fine-tuned on domain-specific academic data. KatzGPT is trained on two university-specific datasets: 6,280 sentence-completion pairs and 7,330 question-answer pairs. KatzBot outperforms established existing open source LLMs, achieving higher accuracy and domain relevance. KatzBot offers a user-friendly interface, significantly enhancing user satisfaction in real-world applications. The source code is publicly available at \url{https://github.com/AiAI-99/katzbot}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_16385 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | KatzBot: Revolutionizing Academic Chatbot for Enhanced Communication Kumar, Sahil Paikar, Deepa Vutukuri, Kiran Sai Ali, Haider Ainala, Shashidhar Reddy Krishnan, Aditya Murli Zhang, Youshan Computation and Language Effective communication within universities is crucial for addressing the diverse information needs of students, alumni, and external stakeholders. However, existing chatbot systems often fail to deliver accurate, context-specific responses, resulting in poor user experiences. In this paper, we present KatzBot, an innovative chatbot powered by KatzGPT, a custom Large Language Model (LLM) fine-tuned on domain-specific academic data. KatzGPT is trained on two university-specific datasets: 6,280 sentence-completion pairs and 7,330 question-answer pairs. KatzBot outperforms established existing open source LLMs, achieving higher accuracy and domain relevance. KatzBot offers a user-friendly interface, significantly enhancing user satisfaction in real-world applications. The source code is publicly available at \url{https://github.com/AiAI-99/katzbot}. |
| title | KatzBot: Revolutionizing Academic Chatbot for Enhanced Communication |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2410.16385 |