UniConv: Unifying Retrieval and Response Generation for Large Language Models in Conversations
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913937805541376 |
|---|---|
| author | Mo, Fengran Gao, Yifan Meng, Chuan Liu, Xin Wu, Zhuofeng Mao, Kelong Wang, Zhengyang Chen, Pei Li, Zheng Li, Xian Yin, Bing Jiang, Meng |
| author_facet | Mo, Fengran Gao, Yifan Meng, Chuan Liu, Xin Wu, Zhuofeng Mao, Kelong Wang, Zhengyang Chen, Pei Li, Zheng Li, Xian Yin, Bing Jiang, Meng |
| contents | The rapid advancement of conversational search systems revolutionizes how information is accessed by enabling the multi-turn interaction between the user and the system. Existing conversational search systems are usually built with two different models. This separation restricts the system from leveraging the intrinsic knowledge of the models simultaneously, which cannot ensure the effectiveness of retrieval benefiting the generation. The existing studies for developing unified models cannot fully address the aspects of understanding conversational context, managing retrieval independently, and generating responses. In this paper, we explore how to unify dense retrieval and response generation for large language models in conversation. We conduct joint fine-tuning with different objectives and design two mechanisms to reduce the inconsistency risks while mitigating data discrepancy. The evaluations on five conversational search datasets demonstrate that our unified model can mutually improve both tasks and outperform the existing baselines. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_07030 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | UniConv: Unifying Retrieval and Response Generation for Large Language Models in Conversations Mo, Fengran Gao, Yifan Meng, Chuan Liu, Xin Wu, Zhuofeng Mao, Kelong Wang, Zhengyang Chen, Pei Li, Zheng Li, Xian Yin, Bing Jiang, Meng Computation and Language Information Retrieval The rapid advancement of conversational search systems revolutionizes how information is accessed by enabling the multi-turn interaction between the user and the system. Existing conversational search systems are usually built with two different models. This separation restricts the system from leveraging the intrinsic knowledge of the models simultaneously, which cannot ensure the effectiveness of retrieval benefiting the generation. The existing studies for developing unified models cannot fully address the aspects of understanding conversational context, managing retrieval independently, and generating responses. In this paper, we explore how to unify dense retrieval and response generation for large language models in conversation. We conduct joint fine-tuning with different objectives and design two mechanisms to reduce the inconsistency risks while mitigating data discrepancy. The evaluations on five conversational search datasets demonstrate that our unified model can mutually improve both tasks and outperform the existing baselines. |
| title | UniConv: Unifying Retrieval and Response Generation for Large Language Models in Conversations |
| topic | Computation and Language Information Retrieval |
| url | https://arxiv.org/abs/2507.07030 |