# UniGDD: A Unified Generative Framework for Goal-Oriented Document-Grounded Dialogue

arXiv: https://arxiv.org/abs/2204.07770 · HTML: https://mlsanity.com/paper/2204.07770/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 26 references that are in the map.
- First posted on arXiv 16 Apr 2022.

## Builds on (most cited first, 16 of 16)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing](https://mlsanity.com/paper/2107.13586/) (2021)
- [A Call for Clarity in Reporting BLEU Scores](https://mlsanity.com/paper/1804.08771/) (2018)
- [A Simple Language Model for Task-Oriented Dialogue](https://mlsanity.com/paper/2005.00796/) (2020)
- [Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systems](https://mlsanity.com/paper/1905.08743/) (2019)
- [Learning End-to-End Goal-Oriented Dialog](https://mlsanity.com/paper/1605.07683/) (2016)
- [doc2dial: A Goal-Oriented Document-Grounded Dialogue Dataset](https://mlsanity.com/paper/2011.06623/) (2020)
- [Beyond Domain APIs: Task-oriented Conversational Modeling with Unstructured Knowledge Access](https://mlsanity.com/paper/2006.03533/) (2020)
- [DIALKI: Knowledge Identification in Conversational Systems through Dialogue-Document Contextualization](https://mlsanity.com/paper/2109.04673/) (2021)
- [Latent Intention Dialogue Models](https://mlsanity.com/paper/1705.10229/) (2017)
- [CAiRE in DialDoc21: Data Augmentation for Information-Seeking Dialogue System](https://mlsanity.com/paper/2106.03530/) (2021)
- [Cascaded Span Extraction and Response Generation for Document-Grounded Dialog](https://mlsanity.com/paper/2106.07275/) (2021)

## Built on by (most cited first, 8 of 8)

- [ChatQA: Surpassing GPT-4 on Conversational QA and RAG](https://mlsanity.com/paper/2401.10225/) (2024)
- [INSCIT: Information-Seeking Conversations with Mixed-Initiative Interactions](https://mlsanity.com/paper/2207.00746/) (2022)
- [Towards Generalizable and Robust Text-to-SQL Parsing](https://mlsanity.com/paper/2210.12674/) (2022)
- [Coarse-to-Fine Knowledge Selection for Document Grounded Dialogs](https://mlsanity.com/paper/2302.11849/) (2023)
- [Causal Document-Grounded Dialogue Pre-training](https://mlsanity.com/paper/2305.10927/) (2023)
- [UniPoll: A Unified Social Media Poll Generation Framework via Multi-Objective Optimization](https://mlsanity.com/paper/2306.06851/) (2023)
- [Structured List-Grounded Question Answering](https://mlsanity.com/paper/2410.03950/) (2024)
- [Structures Facilitate Retrieve, Rerank, and Generate](https://mlsanity.com/paper/2606.03247/) (2026)

## Abstract (arXiv)

The goal-oriented document-grounded dialogue aims at responding to the user query based on the dialogue context and supporting document. Existing studies tackle this problem by decomposing it into two sub-tasks: knowledge identification and response generation. However, such pipeline methods would unavoidably suffer from the error propagation issue. This paper proposes to unify these two sub-tasks via sequentially generating the grounding knowledge and the response. We further develop a prompt-connected multi-task learning strategy to model the characteristics and connections of different tasks and introduce linear temperature scheduling to reduce the negative effect of irrelevant document information. Experimental results demonstrate the effectiveness of our framework.