UniConv: Unifying Retrieval and Response Generation for Large Language Models in Conversations
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Response GenerationSimilar Papers 제목 키워드 기반
UniConvNet: Expanding Effective Receptive Field while Maintaining Asymptotically Gaussian Distribution for ConvNets of Any Scale
Convolutional neural networks (ConvNets) with large effective receptive field (ERF), still in their early stages, have demonstrated promising effectiveness while constrained by high parameters and FLOPs costs and disrupt…
UniConv: A Unified Conversational Neural Architecture for Multi-domain Task-oriented Dialogues
Building an end-to-end conversational agent for multi-domain task-oriented dialogues has been an open challenge for two main reasons. First, tracking dialogue states of multiple domains is non-trivial as the dialogue age…
Dialogue State TrackingTIGeR: Unifying Text-to-Image Generation and Retrieval with Large Multimodal Models
How humans can effectively and efficiently acquire images has always been a perennial question. A classic solution is text-to-image retrieval from an existing database; however, the limited database typically lacks creat…
counterfactualImage GenerationImage RetrievalRetrieval+2From Retrieval to Generation: Unifying External and Parametric Knowledge for Medical Question Answering
Medical question answering (QA) requires extensive access to domain-specific knowledge. A promising direction is to enhance large language models (LLMs) with external knowledge retrieved from medical corpora or parametri…
Question AnsweringAnswer GenerationProvence: efficient and robust context pruning for retrieval-augmented generation
Retrieval-augmented generation improves various aspects of large language models (LLMs) generation, but suffers from computational overhead caused by long contexts as well as the propagation of irrelevant retrieved infor…
Question AnsweringRAGRerankingRetrieval+1