# UniRQR: A Unified Model for Retrieval Decision, Query, and Response Generation in Internet-Based Knowledge Dialogue Systems

arXiv: https://arxiv.org/abs/2401.06811 · HTML: https://mlsanity.com/paper/2401.06811/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 36 references that are in the map.
- First posted on arXiv 11 Jan 2024.

## Builds on (most cited first, 18 of 18)

- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Multitask Prompted Training Enables Zero-Shot Task Generalization](https://mlsanity.com/paper/2110.08207/) (2021)
- [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)
- [Internet-Augmented Dialogue Generation](https://mlsanity.com/paper/2107.07566/) (2021)
- [Knowledge-Grounded Dialogue Generation with Pre-trained Language Models](https://mlsanity.com/paper/2010.08824/) (2020)
- [Language Models that Seek for Knowledge: Modular Search & Generation for Dialogue and Prompt Completion](https://mlsanity.com/paper/2203.13224/) (2022)
- [CPT: A Pre-Trained Unbalanced Transformer for Both Chinese Language Understanding and Generation](https://mlsanity.com/paper/2109.05729/) (2021)
- [A Survey of Knowledge Enhanced Pre-trained Language Models](https://mlsanity.com/paper/2211.05994/) (2022)
- [KdConv: A Chinese Multi-domain Dialogue Dataset Towards Multi-turn Knowledge-driven Conversation](https://mlsanity.com/paper/2004.04100/) (2020)
- [Knowledge Bridging for Empathetic Dialogue Generation](https://mlsanity.com/paper/2009.09708/) (2020)
- [Achieving Reliable Human Assessment of Open-Domain Dialogue Systems](https://mlsanity.com/paper/2203.05899/) (2022)
- [Focused Attention Improves Document-Grounded Generation](https://mlsanity.com/paper/2104.12714/) (2021)
- [Enhancing Dialogue Generation via Dynamic Graph Knowledge Aggregation](https://mlsanity.com/paper/2306.16195/) (2023)
- [Multi-Task Learning of Generation and Classification for Emotion-Aware Dialogue Response Generation](https://mlsanity.com/paper/2105.11696/) (2021)
- [Pretrained Language Models for Dialogue Generation with Multiple Input Sources](https://mlsanity.com/paper/2010.07576/) (2020)
- [Adaptive Bridge between Training and Inference for Dialogue](https://mlsanity.com/paper/2110.11560/) (2021)
- [Dynamically Retrieving Knowledge via Query Generation for Informative Dialogue Generation](https://mlsanity.com/paper/2208.00128/) (2022)

## Abstract (arXiv)

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.