Prompted LLMs as Chatbot Modules for Long Open-domain Conversation
This provides a flexible solution for building consistent chatbots, but it is incremental as it adapts existing prompting methods to a modular framework.
The paper tackles the problem of creating high-quality conversational agents without fine-tuning by proposing MPC, a modular approach using pre-trained LLMs with prompting techniques, and shows it performs on par with fine-tuned models in open-domain conversations.
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.