# End-to-End Autoregressive Retrieval via Bootstrapping for Smart Reply Systems

arXiv: https://arxiv.org/abs/2310.18956 · HTML: https://mlsanity.com/paper/2310.18956/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 11 references that are in the map.
- First posted on arXiv 29 Oct 2023.

## Builds on (most cited first, 6 of 6)

- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Autoregressive Entity Retrieval](https://mlsanity.com/paper/2010.00904/) (2020)
- [Evaluation of Text Generation: A Survey](https://mlsanity.com/paper/2006.14799/) (2020)
- [Efficient Natural Language Response Suggestion for Smart Reply](https://mlsanity.com/paper/1705.00652/) (2017)
- [Distilling Knowledge from Reader to Retriever for Question Answering](https://mlsanity.com/paper/2012.04584/) (2020)
- [OCC: A Smart Reply System for Efficient In-App Communications](https://mlsanity.com/paper/1907.08167/) (2019)

## Built on by (most cited first, 1 of 1)

- [Enhancing AI Assisted Writing with One-Shot Implicit Negative Feedback](https://mlsanity.com/paper/2410.11009/) (2024)

## Abstract (arXiv)

Reply suggestion systems represent a staple component of many instant messaging and email systems. However, the requirement to produce sets of replies, rather than individual replies, makes the task poorly suited for out-of-the-box retrieval architectures, which only consider individual message-reply similarity. As a result, these system often rely on additional post-processing modules to diversify the outputs. However, these approaches are ultimately bottlenecked by the performance of the initial retriever, which in practice struggles to present a sufficiently diverse range of options to the downstream diversification module, leading to the suggestions being less relevant to the user. In this paper, we consider a novel approach that radically simplifies this pipeline through an autoregressive text-to-text retrieval model, that learns the smart reply task end-to-end from a dataset of (message, reply set) pairs obtained via bootstrapping. Empirical results show this method consistently outperforms a range of state-of-the-art baselines across three datasets, corresponding to a 5.1%-17.9% improvement in relevance, and a 0.5%-63.1% improvement in diversity compared to the best baseline approach. We make our code publicly available.