Efficient and Accurate Memorable Conversation Model using DPO based on sLLM

TL;DR

This paper introduces an efficient multi-session dialogue model that manages conversation memory effectively using DPO and SFT techniques, improving accuracy and response quality while maintaining resource efficiency.

Contribution

The paper presents a novel memory management approach in dialogue systems using DPO combined with SFT, achieving superior performance with smaller models.

Findings

Memory accuracy improved by 0.0591 in BERTScore

Response reflection rate increased

Enhanced fluency, coherence, and consistency in responses

Abstract

In multi-session dialog system, it is essential to continuously update the memory as the session progresses. Simply accumulating memory can make it difficult to focus on the content of the conversation for inference due to the limited input sentence size. Therefore, efficient and accurate conversation model that is capable of managing memory to reflect the conversation history continuously is necessary. This paper presents a conversation model that efficiently manages memory as sessions progress and incorporates this into the model to reflect the conversation history accurately with 3 methodologies: SFT, DPO and DPO with SFT model. Our model using DPO algorithm shows an improvement about 0.0591 of BERTScore in memory accuracy, and the rate of responses reflecting the memory increased as well. Also, response generation performance enhanced about 4.292 in fluency, 3.935 in coherence, and 2.896 in consistency. This paper describes a training method that yields better performance than models with more than twice the parameter size, even when the model size is smaller. Thus, our model demonstrates efficiency not only in terms of accuracy but also in resource utilization.