CLAILGMay 8, 2023

Prompted LLMs as Chatbot Modules for Long Open-domain Conversation

arXiv:2305.04533v1259 citations
Originality Incremental advance
AI Analysis

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes