# Retrieve and Refine: Improved Sequence Generation Models For Dialogue

arXiv: https://arxiv.org/abs/1808.04776 · HTML: https://mlsanity.com/paper/1808.04776/

## Key facts

- Cited by 82 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Aug 2018.

## Built on by (most cited first, 30 of 82)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [What Makes Good In-Context Examples for GPT-3?](https://mlsanity.com/paper/2101.06804/) (2021)
- ["I'm sorry to hear that": Finding New Biases in Language Models with a Holistic Descriptor Dataset](https://mlsanity.com/paper/2205.09209/) (2022)
- [A Survey on Retrieval-Augmented Text Generation](https://mlsanity.com/paper/2202.01110/) (2022)
- [Case-based Reasoning for Natural Language Queries over Knowledge Bases](https://mlsanity.com/paper/2104.08762/) (2021)
- [Lift Yourself Up: Retrieval-augmented Text Generation with Self Memory](https://mlsanity.com/paper/2305.02437/) (2023)
- [Retrieving Multimodal Information for Augmented Generation: A Survey](https://mlsanity.com/paper/2303.10868/) (2023)
- [Improving Named Entity Recognition by External Context Retrieving and Cooperative Learning](https://mlsanity.com/paper/2105.03654/) (2021)
- [Leveraging Large Language Models in Conversational Recommender Systems](https://mlsanity.com/paper/2305.07961/) (2023)
- [Neural Machine Translation with Monolingual Translation Memory](https://mlsanity.com/paper/2105.11269/) (2021)
- [kNN Prompting: Beyond-Context Learning with Calibration-Free Nearest Neighbor Inference](https://mlsanity.com/paper/2303.13824/) (2023)
- [AlphaFin: Benchmarking Financial Analysis with Retrieval-Augmented Stock-Chain Framework](https://mlsanity.com/paper/2403.12582/) (2024)
- [Good for Misconceived Reasons: An Empirical Revisiting on the Need for Visual Context in Multimodal Machine Translation](https://mlsanity.com/paper/2105.14462/) (2021)
- [Goldfish: Vision-Language Understanding of Arbitrarily Long Videos](https://mlsanity.com/paper/2407.12679/) (2024)
- [Fast Nearest Neighbor Machine Translation](https://mlsanity.com/paper/2105.14528/) (2021)
- [A Survey on Knowledge-Oriented Retrieval-Augmented Generation](https://mlsanity.com/paper/2503.10677/) (2025)
- [Controllable Semantic Parsing via Retrieval Augmentation](https://mlsanity.com/paper/2110.08458/) (2021)
- [Retrieval-augmented Image Captioning](https://mlsanity.com/paper/2302.08268/) (2023)
- [WebBrain: Learning to Generate Factually Correct Articles for Queries by Grounding on Large Web Corpus](https://mlsanity.com/paper/2304.04358/) (2023)
- [Stochastic RAG: End-to-End Retrieval-Augmented Generation through Expected Utility Maximization](https://mlsanity.com/paper/2405.02816/) (2024)
- [Copy Is All You Need](https://mlsanity.com/paper/2307.06962/) (2023)
- [Building a Role Specified Open-Domain Dialogue System Leveraging Large-Scale Language Models](https://mlsanity.com/paper/2205.00176/) (2022)
- [CORE: A Retrieve-then-Edit Framework for Counterfactual Data Generation](https://mlsanity.com/paper/2210.04873/) (2022)
- [Jill Watson: A Virtual Teaching Assistant powered by ChatGPT](https://mlsanity.com/paper/2405.11070/) (2024)
- [Hi, my name is Martha: Using names to measure and mitigate bias in generative dialogue models](https://mlsanity.com/paper/2109.03300/) (2021)
- [Towards a Search Engine for Machines: Unified Ranking for Multiple Retrieval-Augmented Large Language Models](https://mlsanity.com/paper/2405.00175/) (2024)
- [Crossing the Conversational Chasm: A Primer on Natural Language Processing for Multilingual Task-Oriented Dialogue Systems](https://mlsanity.com/paper/2104.08570/) (2021)
- [Retrieval-Augmented Multilingual Keyphrase Generation with Retriever-Generator Iterative Training](https://mlsanity.com/paper/2205.10471/) (2022)
- [RETRONLU: Retrieval Augmented Task-Oriented Semantic Parsing](https://mlsanity.com/paper/2109.10410/) (2021)
- [Unsupervised Enrichment of Persona-grounded Dialog with Background Stories](https://mlsanity.com/paper/2106.08364/) (2021)

## Abstract (arXiv)

Sequence generation models for dialogue are known to have several problems: they tend to produce short, generic sentences that are uninformative and unengaging. Retrieval models on the other hand can surface interesting responses, but are restricted to the given retrieval set leading to erroneous replies that cannot be tuned to the specific context. In this work we develop a model that combines the two approaches to avoid both their deficiencies: first retrieve a response and then refine it -- the final sequence generator treating the retrieval as additional context. We show on the recent CONVAI2 challenge task our approach produces responses superior to both standard retrieval and generation models in human evaluations.