# Multi-Party Supervised Fine-tuning of Language Models for Multi-Party Dialogue Generation

arXiv: https://arxiv.org/abs/2412.05342 · HTML: https://mlsanity.com/paper/2412.05342/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 28 references that are in the map.
- First posted on arXiv 6 Dec 2024.

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

- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them](https://mlsanity.com/paper/2210.09261/) (2022)
- [LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models](https://mlsanity.com/paper/2403.13372/) (2024)
- [DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model](https://mlsanity.com/paper/2405.04434/) (2024)
- [Improving Language Model Negotiation with Self-Play and In-Context Learning from AI Feedback](https://mlsanity.com/paper/2305.10142/) (2023)
- [ChatHaruhi: Reviving Anime Character in Reality via Large Language Model](https://mlsanity.com/paper/2308.09597/) (2023)
- [Experiential Co-Learning of Software-Developing Agents](https://mlsanity.com/paper/2312.17025/) (2023)
- [Self-Alignment of Large Language Models via Monopolylogue-based Social Scene Simulation](https://mlsanity.com/paper/2402.05699/) (2024)
- [MPC-BERT: A Pre-Trained Language Model for Multi-Party Conversation Understanding](https://mlsanity.com/paper/2106.01541/) (2021)
- [Conversational flow in Oxford-style debates](https://mlsanity.com/paper/1604.03114/) (2016)
- [Addressee and Response Selection in Multi-Party Conversations with Speaker Interaction RNNs](https://mlsanity.com/paper/1709.04005/) (2017)
- [Debatrix: Multi-dimensional Debate Judge with Iterative Chronological Analysis Based on LLM](https://mlsanity.com/paper/2403.08010/) (2024)
- [Can LLMs Beat Humans in Debating? A Dynamic Multi-agent Framework for Competitive Debate](https://mlsanity.com/paper/2408.04472/) (2024)
- [Generic Dependency Modeling for Multi-Party Conversation](https://mlsanity.com/paper/2302.10680/) (2023)

## Built on by (most cited first, 6 of 6)

- [A Survey on LLM-based Conversational User Simulation](https://mlsanity.com/paper/2604.24977/) (2026)
- [Multi-Party Conversational Agents: A Survey](https://mlsanity.com/paper/2505.18845/) (2025)
- [Speak or Stay Silent: Context-Aware Turn-Taking in Multi-Party Dialogue](https://mlsanity.com/paper/2603.11409/) (2026)
- [Contrastive Speaker-Aware Learning for Multi-party Dialogue Generation with LLMs](https://mlsanity.com/paper/2503.08842/) (2025)
- [Evaluating LLM-Simulated Conversations in Modeling Inconsistent and Uncollaborative Behaviors in Human Social Interaction](https://mlsanity.com/paper/2603.17094/) (2026)
- [EGCForest: Structured Agent Memory Organization for Enterprise Group Chats](https://mlsanity.com/paper/2610.19836/) (2026)

## Abstract (arXiv)

Large Language Models (LLM) are usually fine-tuned to participate in dyadic or two-party dialogues, which can not adapt well to multi-party dialogues (MPD), which hinders their applications in such scenarios including multi-personal meetings, discussions and daily communication. Previous LLM-based researches mainly focus on the multi-agent framework, while their base LLMs are still pairwisely fine-tuned. In this work, we design a multi-party fine-tuning framework (MuPaS) for LLMs on the multi-party dialogue datasets, and prove such a straightforward framework can let the LLM align with the multi-party conversation style efficiently and effectively. We also design two training strategies which can convert MuPaS into the MPD simulator. Substantial experiments show that MuPaS can achieve state-of-the-art multi-party response, higher accuracy of the-next-speaker prediction, higher human and automatic evaluated utterance qualities, and can even generate reasonably with out-of-distribution scene, topic and role descriptions. The MuPaS framework bridges the LLM training with more complicated multi-party applications, such as conversation generation, virtual rehearsal or meta-universe.