UniRQR: A Unified Model for Retrieval Decision, Query, and Response Generation in Internet-Based Knowledge Dialogue Systems
This work addresses a critical oversight in knowledge-based dialogue systems for practical applications, though it is incremental as it builds on existing multi-task and prompt learning approaches.
The paper tackles the problem of over-reliance on external knowledge in internet-based dialogue systems by proposing a unified model that jointly handles retrieval decision, query generation, and response generation, achieving performance comparable to state-of-the-art specialized models on Wizint and Dusinc datasets.
Knowledge-based dialogue systems with internet retrieval have recently attracted considerable attention from researchers. The dialogue systems overcome a major limitation of traditional knowledge dialogue systems, where the timeliness of knowledge cannot be assured, hence providing greater practical application value. Knowledge-based dialogue systems with internet retrieval can be typically segmented into three tasks: Retrieval Decision, Query Generation, and Response Generation. However, many of studies assumed that all conversations require external knowledge to continue, neglecting the critical step of determining when retrieval is necessary. This assumption often leads to an over-dependence on external knowledge, even when it may not be required. Our work addresses this oversight by employing a single unified model facilitated by prompt and multi-task learning approaches. This model not only decides whether retrieval is necessary but also generates retrieval queries and responses. By integrating these functions, our system leverages the full potential of pre-trained models and reduces the complexity and costs associated with deploying multiple models. We conducted extensive experiments to investigate the mutual enhancement among the three tasks in our system. What is more, the experiment results on the Wizint and Dusinc datasets not only demonstrate that our unified model surpasses the baseline performance for individual tasks, but also reveal that it achieves comparable results when contrasted with SOTA systems that deploy separate, specialized models for each task.