Multi-Party Supervised Fine-tuning of Language Models for Multi-Party Dialogue Generation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866918054157352960 |
|---|---|
| author | Wang, Xiaoyu Xi, Ningyuan Chen, Teng Gu, Qingqing Zhao, Yue Chen, Xiaokai Jiang, Zhonglin Chen, Yong Ji, Luo |
| author_facet | Wang, Xiaoyu Xi, Ningyuan Chen, Teng Gu, Qingqing Zhao, Yue Chen, Xiaokai Jiang, Zhonglin Chen, Yong Ji, Luo |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_05342 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Multi-Party Supervised Fine-tuning of Language Models for Multi-Party Dialogue Generation Wang, Xiaoyu Xi, Ningyuan Chen, Teng Gu, Qingqing Zhao, Yue Chen, Xiaokai Jiang, Zhonglin Chen, Yong Ji, Luo Computation and Language Artificial Intelligence 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. |
| title | Multi-Party Supervised Fine-tuning of Language Models for Multi-Party Dialogue Generation |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2412.05342 |