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

arXiv: https://arxiv.org/abs/2502.17328 · HTML: https://mlsanity.com/paper/2502.17328/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 38 references that are in the map.
- First posted on arXiv 24 Feb 2025.

## Builds on (most cited first, 26 of 26)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models](https://mlsanity.com/paper/2401.01335/) (2024)
- [SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarization](https://mlsanity.com/paper/1911.12237/) (2019)
- [Reinforced Self-Training (ReST) for Language Modeling](https://mlsanity.com/paper/2308.08998/) (2023)
- [ZeroGen: Efficient Zero-shot Learning via Dataset Generation](https://mlsanity.com/paper/2202.07922/) (2022)
- [Generating Training Data with Language Models: Towards Zero-Shot Language Understanding](https://mlsanity.com/paper/2202.04538/) (2022)
- [DialogSum: A Real-Life Scenario Dialogue Summarization Dataset](https://mlsanity.com/paper/2105.06762/) (2021)
- [MedDialog: Two Large-scale Medical Dialogue Datasets](https://mlsanity.com/paper/2004.03329/) (2020)
- [Exploiting Asymmetry for Synthetic Training Data Generation: SynthIE and the Case of Information Extraction](https://mlsanity.com/paper/2303.04132/) (2023)
- [Medically Aware GPT-3 as a Data Generator for Medical Dialogue Summarization](https://mlsanity.com/paper/2110.07356/) (2021)
- [DialogLM: Pre-trained Model for Long Dialogue Understanding and Summarization](https://mlsanity.com/paper/2109.02492/) (2021)
- [ProGen: Progressive Zero-shot Dataset Generation via In-context Feedback](https://mlsanity.com/paper/2210.12329/) (2022)
- [Synthesizing Text-to-SQL Data from Weak and Strong LLMs](https://mlsanity.com/paper/2408.03256/) (2024)
- [AdaptSum: Towards Low-Resource Domain Adaptation for Abstractive Summarization](https://mlsanity.com/paper/2103.11332/) (2021)
- [TWEETSUMM -- A Dialog Summarization Dataset for Customer Service](https://mlsanity.com/paper/2111.11894/) (2021)
- [Low-Resource Dialogue Summarization with Domain-Agnostic Multi-Source Pretraining](https://mlsanity.com/paper/2109.04080/) (2021)
- [TODSum: Task-Oriented Dialogue Summarization with State Tracking](https://mlsanity.com/paper/2110.12680/) (2021)
- [LAD: Language Models as Data for Zero-Shot Dialog](https://mlsanity.com/paper/2207.14393/) (2022)
- [SynthDST: Synthetic Data is All You Need for Few-Shot Dialog State Tracking](https://mlsanity.com/paper/2402.02285/) (2024)
- [Domain-Oriented Prefix-Tuning: Towards Efficient and Generalizable Fine-tuning for Zero-Shot Dialogue Summarization](https://mlsanity.com/paper/2204.04362/) (2022)
- [A Survey on Medical Document Summarization](https://mlsanity.com/paper/2212.01669/) (2022)
- [DIONYSUS: A Pre-trained Model for Low-Resource Dialogue Summarization](https://mlsanity.com/paper/2212.10018/) (2022)
- [Semi-Supervised Dialogue Abstractive Summarization via High-Quality Pseudolabel Selection](https://mlsanity.com/paper/2403.04073/) (2024)
- [Few-Shot Dialogue Summarization via Skeleton-Assisted Prompt Transfer in Prompt Tuning](https://mlsanity.com/paper/2305.12077/) (2023)

## Built on by (most cited first, 5 of 5)

- [Reasoning or Not? A Comprehensive Evaluation of Reasoning LLMs for Dialogue Summarization](https://mlsanity.com/paper/2507.02145/) (2025)
- [Spoken DialogSum: An Emotion-Rich Conversational Dataset for Spoken Dialogue Summarization](https://mlsanity.com/paper/2512.14687/) (2025)
- [Paired by the Teacher: Turning Unpaired Data into High-Fidelity Pairs for Low-Resource Text Generation](https://mlsanity.com/paper/2509.25144/) (2025)
- [Beyond Overlap Metrics: Rewarding Reasoning and Preferences for Faithful Multi-Role Dialogue Summarization](https://mlsanity.com/paper/2604.17188/) (2026)
- [BridgeAlign: Bridging Preference Alignment for Humanities and Social Sciences](https://mlsanity.com/paper/2607.27366/) (2026)

## Abstract (arXiv)

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.