# Retrieval-Enhanced Adversarial Training for Neural Response Generation

arXiv: https://arxiv.org/abs/1809.04276 · HTML: https://mlsanity.com/paper/1809.04276/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Sep 2018.

## Built on by (most cited first, 22 of 22)

- [Recent Advances in Deep Learning Based Dialogue Systems: A Systematic Survey](https://mlsanity.com/paper/2105.04387/) (2021)
- [A Complete Survey on Generative AI (AIGC): Is ChatGPT from GPT-4 to GPT-5 All You Need?](https://mlsanity.com/paper/2303.11717/) (2023)
- [TextStyleBrush: Transfer of Text Aesthetics from a Single Example](https://mlsanity.com/paper/2106.08385/) (2021)
- [De-rendering Stylized Texts](https://mlsanity.com/paper/2110.01890/) (2021)
- [AGTGAN: Unpaired Image Translation for Photographic Ancient Character Generation](https://mlsanity.com/paper/2303.07012/) (2023)
- [STRIVE: Scene Text Replacement In Videos](https://mlsanity.com/paper/2109.02762/) (2021)
- [Recall and Learn: A Memory-augmented Solver for Math Word Problems](https://mlsanity.com/paper/2109.13112/) (2021)
- [Report from the NSF Future Directions Workshop on Automatic Evaluation of Dialog: Research Directions and Challenges](https://mlsanity.com/paper/2203.10012/) (2022)
- [GenText: Unsupervised Artistic Text Generation via Decoupled Font and Texture Manipulation](https://mlsanity.com/paper/2207.09649/) (2022)
- [A Template-guided Hybrid Pointer Network for Knowledge-basedTask-oriented Dialogue Systems](https://mlsanity.com/paper/2106.05830/) (2021)
- [Alleviating the Long-Tail Problem in Conversational Recommender Systems](https://mlsanity.com/paper/2307.11650/) (2023)
- [Communication is All You Need: Persuasion Dataset Construction via Multi-LLM Communication](https://mlsanity.com/paper/2502.08896/) (2025)
- [Scalable Font Reconstruction with Dual Latent Manifolds](https://mlsanity.com/paper/2109.06627/) (2021)
- [A Survey on Natural Language Processing for Programming](https://mlsanity.com/paper/2212.05773/) (2022)
- [Lexical Knowledge Internalization for Neural Dialog Generation](https://mlsanity.com/paper/2205.01941/) (2022)
- [CORAL: Contextual Response Retrievability Loss Function for Training Dialog Generation Models](https://mlsanity.com/paper/2205.10558/) (2022)
- [A Neural Conversation Generation Model via Equivalent Shared Memory Investigation](https://mlsanity.com/paper/2108.09164/) (2021)
- [HeroNet: A Hybrid Retrieval-Generation Network for Conversational Bots](https://mlsanity.com/paper/2301.12400/) (2023)
- [A Conditional Generative Chatbot using Transformer Model](https://mlsanity.com/paper/2306.02074/) (2023)
- [A Stack-Propagation Framework for Low-Resource Personalized Dialogue Generation](https://mlsanity.com/paper/2410.20174/) (2024)
- [A Static and Dynamic Attention Framework for Multi Turn Dialogue Generation](https://mlsanity.com/paper/2410.20766/) (2024)
- [SpheriCity: Designing Trustworthy Conversational AI for Sustainability Decision Support](https://mlsanity.com/paper/2606.13854/) (2026)

## Abstract (arXiv)

Dialogue systems are usually built on either generation-based or retrieval-based approaches, yet they do not benefit from the advantages of different models. In this paper, we propose a Retrieval-Enhanced Adversarial Training (REAT) method for neural response generation. Distinct from existing approaches, the REAT method leverages an encoder-decoder framework in terms of an adversarial training paradigm, while taking advantage of N-best response candidates from a retrieval-based system to construct the discriminator. An empirical study on a large scale public available benchmark dataset shows that the REAT method significantly outperforms the vanilla Seq2Seq model as well as the conventional adversarial training approach.