Prompted LLMs as Chatbot Modules for Long Open-domain Conversation

Gibbeum Lee; Volker Hartmann; Jongho Park; Dimitris Papailiopoulos; Kangwook Lee

ACL 2023findings72 citations

Prompted LLMs as Chatbot Modules for Long Open-domain Conversation

Gibbeum Lee, Volker Hartmann, Jongho Park, Dimitris Papailiopoulos, Kangwook Lee

Abstract

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.

BibTeX

@inproceedings{lee-etal-2023-prompted,
    title = "Prompted {LLM}s as Chatbot Modules for Long Open-domain Conversation",
    author = "Lee, Gibbeum  and
      Hartmann, Volker  and
      Park, Jongho  and
      Papailiopoulos, Dimitris  and
      Lee, Kangwook",
    editor = "Rogers, Anna  and
      Boyd-Graber, Jordan  and
      Okazaki, Naoaki",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2023",
    month = jul,
    year = "2023",
    address = "Toronto, Canada",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2023.findings-acl.277/",
    doi = "10.18653/v1/2023.findings-acl.277",
    pages = "4536--4554"
}