In this paper, we propose MPC (Modular Prompted Chatbot), a new approach for creating high-quality conversational agents without the need for fine-tuning. Our method utilizes pre-trained large language models (LLMs) as individual modules for long-term consistency and flexibility, by using techniques such as few-shot prompting, chain-of-thought (CoT), and external memory. Our human evaluation results show that MPC is on par with fine-tuned chatbot models in open-domain conversations, making it an effective solution for creating consistent and engaging chatbots.
@article{arxiv.2305.04533,
title = {Prompted LLMs as Chatbot Modules for Long Open-domain Conversation},
author = {Gibbeum Lee and Volker Hartmann and Jongho Park and Dimitris Papailiopoulos and Kangwook Lee},
journal= {arXiv preprint arXiv:2305.04533},
year = {2023}
}
Comments
Accepted to the Findings of ACL2023. The camera-ready version with additional experimental results will be uploaded