Mutual Reinforcement of LLM Dialogue Synthesis and Summarization Capabilities for Few-Shot Dialogue Summarization

TL;DR

This paper introduces a mutual reinforcement data synthesis method within large language models to enhance few-shot dialogue summarization by mutually improving dialogue generation and summarization capabilities, leading to better performance and human evaluation scores.

Contribution

The paper presents a novel mutual reinforcement mechanism that leverages internal LLM knowledge to generate synthetic data, improving dialogue summarization without external resources.

Findings

Achieved 1.5% higher ROUGE scores in few-shot settings.

Improved BERT scores by 0.3% in experiments.

Outperformed baselines in human evaluations.

Abstract

In this work, we propose Mutual Reinforcing Data Synthesis (MRDS) within LLMs to improve few-shot dialogue summarization task. Unlike prior methods that require external knowledge, we mutually reinforce the LLM\'s dialogue synthesis and summarization capabilities, allowing them to complement each other during training and enhance overall performances. The dialogue synthesis capability is enhanced by directed preference optimization with preference scoring from summarization capability. The summarization capability is enhanced by the additional high quality dialogue-summary paired data produced by the dialogue synthesis capability. By leveraging the proposed MRDS mechanism, we elicit the internal knowledge of LLM in the format of synthetic data, and use it to augment the few-shot real training dataset. Empirical results demonstrate that our method improves dialogue summarization, achieving a 1.5% increase in ROUGE scores and a 0.3% improvement in BERT scores in few-shot settings. Furthermore, our method attains the highest average scores in human evaluations, surpassing both the pre-trained models and the baselines fine-tuned solely for summarization tasks.