# Query Enhanced Knowledge-Intensive Conversation via Unsupervised Joint Modeling

Source: [Query Enhanced Knowledge-Intensive Conversation via Unsupervised Joint Modeling](<https://www.sota2.com/research/paper/68fa6f7f1e209131cea45fa8>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T01:21:27.030Z

Authors: Mingzhu Cai, Siqi Bao, Xin Tian, Huang He, Fan Wang, Hua Wu

Published: 2022-12-19T16:21:05.000Z

## Abstract

In this paper, we propose an unsupervised query enhanced approach for knowledge-intensive conversations, namely QKConv. There are three modules in QKConv: a query generator, an off-the-shelf knowledge selector, and a response generator. QKConv is optimized through joint training, which produces the response by exploring multiple candidate queries and leveraging corresponding selected knowledge. The joint training solely relies on the dialogue context and target response, getting exempt from extra query annotations or knowledge provenances. To evaluate the effectiveness of the proposed QKConv, we conduct experiments on three representative knowledge-intensive conversation datasets: conversational question-answering, task-oriented dialogue, and knowledge-grounded conversation. Experimental results reveal that QKConv performs better than all unsupervised methods across three datasets and achieves competitive performance compared to supervised methods.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2212.09588>)

[PDF](<https://arxiv.org/pdf/2212.09588.pdf>)
