# Advancing Multi-Party Dialogue Framework with Speaker-ware Contrastive Learning

arXiv: https://arxiv.org/abs/2501.11292 · HTML: https://mlsanity.com/paper/2501.11292/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 31 references that are in the map.
- First posted on arXiv 20 Jan 2025.

## Builds on (most cited first, 17 of 17)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [The Ubuntu Dialogue Corpus: A Large Dataset for Research in Unstructured Multi-Turn Dialogue Systems](https://mlsanity.com/paper/1506.08909/) (2015)
- [A Deep Sequential Model for Discourse Parsing on Multi-Party Dialogues](https://mlsanity.com/paper/1812.00176/) (2018)
- [DialogVED: A Pre-trained Latent Variable Encoder-Decoder Model for Dialog Response Generation](https://mlsanity.com/paper/2204.13031/) (2022)
- [Multimodal Dialogue Response Generation](https://mlsanity.com/paper/2110.08515/) (2021)
- [GSN: A Graph-Structured Network for Multi-Party Dialogues](https://mlsanity.com/paper/1905.13637/) (2019)
- [Filling the Gap of Utterance-aware and Speaker-aware Representation for Multi-turn Dialogue](https://mlsanity.com/paper/2009.06504/) (2020)
- [Response Selection for Multi-Party Conversations with Dynamic Topic Tracking](https://mlsanity.com/paper/2010.07785/) (2020)
- [Topic-Aware Contrastive Learning for Abstractive Dialogue Summarization](https://mlsanity.com/paper/2109.04994/) (2021)
- [HeterMPC: A Heterogeneous Graph Neural Network for Response Generation in Multi-Party Conversations](https://mlsanity.com/paper/2203.08500/) (2022)
- [Multi-Task Learning of Generation and Classification for Emotion-Aware Dialogue Response Generation](https://mlsanity.com/paper/2105.11696/) (2021)
- [Enhanced Speaker-aware Multi-party Multi-turn Dialogue Comprehension](https://mlsanity.com/paper/2109.04066/) (2021)
- [SocialNLP EmotionX 2019 Challenge Overview: Predicting Emotions in Spoken Dialogues and Chats](https://mlsanity.com/paper/1909.07734/) (2019)
- [MADNet: Maximizing Addressee Deduction Expectation for Multi-Party Conversation Generation](https://mlsanity.com/paper/2305.12733/) (2023)
- [Dynamically Retrieving Knowledge via Query Generation for Informative Dialogue Generation](https://mlsanity.com/paper/2208.00128/) (2022)

## Built on by (most cited first, 1 of 1)

- [Evaluating Long-Horizon Memory for Multi-Party Collaborative Dialogues](https://mlsanity.com/paper/2602.01313/) (2026)

## Abstract (arXiv)

Multi-party dialogues, common in collaborative scenarios like brainstorming sessions and negotiations, pose significant challenges due to their complexity and diverse speaker roles. Current methods often use graph neural networks to model dialogue context, capturing structural dynamics but heavily relying on annotated graph structures and overlooking individual speaking styles. To address these challenges, we propose CMR, a Contrastive learning-based Multi-party dialogue Response generation framework. CMR employs a two-stage self-supervised contrastive learning framework. First, it captures global differences in speaking styles across individuals. Then, it focuses on intra-conversation comparisons to identify thematic transitions and contextually relevant facts. To the best of our knowledge, this is the first approach that applies contrastive learning in multi-party dialogue generation. Experimental results demonstrate that CMR not only significantly outperforms state-of-the-art models, but also generalizes well to large pre-trained language models, effectively enhancing their capability in handling multi-party conversations.