# Two are Better than One: An Ensemble of Retrieval- and Generation-Based Dialog Systems

arXiv: https://arxiv.org/abs/1610.07149 · HTML: https://mlsanity.com/paper/1610.07149/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Oct 2016.

## Built on by (most cited first, 13 of 13)

- [What Makes Good In-Context Examples for GPT-3?](https://mlsanity.com/paper/2101.06804/) (2021)
- [A Survey on Retrieval-Augmented Text Generation](https://mlsanity.com/paper/2202.01110/) (2022)
- [Recent Advances in Deep Learning Based Dialogue Systems: A Systematic Survey](https://mlsanity.com/paper/2105.04387/) (2021)
- [Lift Yourself Up: Retrieval-augmented Text Generation with Self Memory](https://mlsanity.com/paper/2305.02437/) (2023)
- [Injecting New Knowledge into Large Language Models via Supervised Fine-Tuning](https://mlsanity.com/paper/2404.00213/) (2024)
- [On the Way to LLM Personalization: Learning to Remember User Conversations](https://mlsanity.com/paper/2411.13405/) (2024)
- [Seamlessly Integrating Factual Information and Social Content with Persuasive Dialogue](https://mlsanity.com/paper/2203.07657/) (2022)
- [Meta-evaluation of Conversational Search Evaluation Metrics](https://mlsanity.com/paper/2104.13453/) (2021)
- [Improving Automated Evaluation of Open Domain Dialog via Diverse Reference Augmentation](https://mlsanity.com/paper/2106.02833/) (2021)
- [Data-to-text Generation by Splicing Together Nearest Neighbors](https://mlsanity.com/paper/2101.08248/) (2021)
- [A Neural Conversation Generation Model via Equivalent Shared Memory Investigation](https://mlsanity.com/paper/2108.09164/) (2021)
- [Let's Get Personal: Personal Questions Improve SocialBot Performance in the Alexa Prize](https://mlsanity.com/paper/2303.04953/) (2023)
- [KORE: Enhancing Knowledge Injection for Large Multimodal Models via Knowledge-Oriented Controls](https://mlsanity.com/paper/2510.19316/) (2025)

## Abstract (arXiv)

Open-domain human-computer conversation has attracted much attention in the field of NLP. Contrary to rule- or template-based domain-specific dialog systems, open-domain conversation usually requires data-driven approaches, which can be roughly divided into two categories: retrieval-based and generation-based systems. Retrieval systems search a user-issued utterance (called a query) in a large database, and return a reply that best matches the query. Generative approaches, typically based on recurrent neural networks (RNNs), can synthesize new replies, but they suffer from the problem of generating short, meaningless utterances. In this paper, we propose a novel ensemble of retrieval-based and generation-based dialog systems in the open domain. In our approach, the retrieved candidate, in addition to the original query, is fed to an RNN-based reply generator, so that the neural model is aware of more information. The generated reply is then fed back as a new candidate for post-reranking. Experimental results show that such ensemble outperforms each single part of it by a large margin.