# GIFT: Graph-Induced Fine-Tuning for Multi-Party Conversation Understanding

arXiv: https://arxiv.org/abs/2305.09360 · HTML: https://mlsanity.com/paper/2305.09360/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 35 references that are in the map.
- First posted on arXiv 16 May 2023.

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

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation](https://mlsanity.com/paper/1911.00536/) (2019)
- [Recipes for building an open-domain chatbot](https://mlsanity.com/paper/2004.13637/) (2020)
- [Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models](https://mlsanity.com/paper/1507.04808/) (2015)
- [Neural Responding Machine for Short-Text Conversation](https://mlsanity.com/paper/1503.02364/) (2015)
- [Sequential Matching Network: A New Architecture for Multi-turn Response Selection in Retrieval-based Chatbots](https://mlsanity.com/paper/1612.01627/) (2016)
- [Speaker-Aware BERT for Multi-Turn Response Selection in Retrieval-Based Chatbots](https://mlsanity.com/paper/2004.03588/) (2020)
- [MPC-BERT: A Pre-Trained Language Model for Multi-Party Conversation Understanding](https://mlsanity.com/paper/2106.01541/) (2021)
- [GSN: A Graph-Structured Network for Multi-Party Dialogues](https://mlsanity.com/paper/1905.13637/) (2019)
- [Response Selection for Multi-Party Conversations with Dynamic Topic Tracking](https://mlsanity.com/paper/2010.07785/) (2020)
- [Addressee and Response Selection in Multi-Party Conversations with Speaker Interaction RNNs](https://mlsanity.com/paper/1709.04005/) (2017)
- [HeterMPC: A Heterogeneous Graph Neural Network for Response Generation in Multi-Party Conversations](https://mlsanity.com/paper/2203.08500/) (2022)
- [Towards Neural Speaker Modeling in Multi-Party Conversation: The Task, Dataset, and Models](https://mlsanity.com/paper/1708.03152/) (2017)
- [Unsupervised Conversation Disentanglement through Co-Training](https://mlsanity.com/paper/2109.03199/) (2021)
- [Back to the Future: Bidirectional Information Decoupling Network for Multi-turn Dialogue Modeling](https://mlsanity.com/paper/2204.08152/) (2022)

## Built on by (most cited first, 10 of 10)

- [Multi-User Chat Assistant (MUCA): a Framework Using LLMs to Facilitate Group Conversations](https://mlsanity.com/paper/2401.04883/) (2024)
- [Is ChatGPT a Good Multi-Party Conversation Solver?](https://mlsanity.com/paper/2310.16301/) (2023)
- [Do LLMs suffer from Multi-Party Hangover? A Diagnostic Approach to Addressee Recognition and Response Selection in Conversations](https://mlsanity.com/paper/2409.18602/) (2024)
- [Multi-Party Conversational Agents: A Survey](https://mlsanity.com/paper/2505.18845/) (2025)
- [Multi-turn Dialogue Comprehension from a Topic-aware Perspective](https://mlsanity.com/paper/2309.09666/) (2023)
- [The Future of Cognitive Strategy-enhanced Persuasive Dialogue Agents: New Perspectives and Trends](https://mlsanity.com/paper/2402.04631/) (2024)
- [Multimodal Conversation Structure Understanding](https://mlsanity.com/paper/2505.17536/) (2025)
- [SS-MPC: A Sequence-Structured Multi-Party Conversation System](https://mlsanity.com/paper/2502.16920/) (2025)
- [GroupGPT: A Token-efficient and Privacy-preserving Agentic Framework for Multi-User Chat Assistant](https://mlsanity.com/paper/2603.01059/) (2026)
- [GCAgent: Enhancing Group Chat Communication through Dialogue Agents System](https://mlsanity.com/paper/2603.05240/) (2026)

## Abstract (arXiv)

Addressing the issues of who saying what to whom in multi-party conversations (MPCs) has recently attracted a lot of research attention. However, existing methods on MPC understanding typically embed interlocutors and utterances into sequential information flows, or utilize only the superficial of inherent graph structures in MPCs. To this end, we present a plug-and-play and lightweight method named graph-induced fine-tuning (GIFT) which can adapt various Transformer-based pre-trained language models (PLMs) for universal MPC understanding. In detail, the full and equivalent connections among utterances in regular Transformer ignore the sparse but distinctive dependency of an utterance on another in MPCs. To distinguish different relationships between utterances, four types of edges are designed to integrate graph-induced signals into attention mechanisms to refine PLMs originally designed for processing sequential texts. We evaluate GIFT by implementing it into three PLMs, and test the performance on three downstream tasks including addressee recognition, speaker identification and response selection. Experimental results show that GIFT can significantly improve the performance of three PLMs on three downstream tasks and two benchmarks with only 4 additional parameters per encoding layer, achieving new state-of-the-art performance on MPC understanding.