# An Adversarially-Learned Turing Test for Dialog Generation Models

arXiv: https://arxiv.org/abs/2104.08231 · HTML: https://mlsanity.com/paper/2104.08231/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 38 references that are in the map.
- First posted on arXiv 16 Apr 2021.

## Builds on (most cited first, 27 of 27)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [BLEURT: Learning Robust Metrics for Text Generation](https://mlsanity.com/paper/2004.04696/) (2020)
- [A Diversity-Promoting Objective Function for Neural Conversation Models](https://mlsanity.com/paper/1510.03055/) (2015)
- [DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation](https://mlsanity.com/paper/1911.00536/) (2019)
- [Evasion Attacks against Machine Learning at Test Time](https://mlsanity.com/paper/1708.06131/) (2017)
- [Generating Natural Language Adversarial Examples](https://mlsanity.com/paper/1804.07998/) (2018)
- [TextBugger: Generating Adversarial Text Against Real-world Applications](https://mlsanity.com/paper/1812.05271/) (2018)
- [Black-box Generation of Adversarial Text Sequences to Evade Deep Learning Classifiers](https://mlsanity.com/paper/1801.04354/) (2018)
- [Deep Reinforcement Learning for Dialogue Generation](https://mlsanity.com/paper/1606.01541/) (2016)
- [Adversarial Training Methods for Semi-Supervised Text Classification](https://mlsanity.com/paper/1605.07725/) (2016)
- [Generating Natural Adversarial Examples](https://mlsanity.com/paper/1710.11342/) (2017)
- [Build it Break it Fix it for Dialogue Safety: Robustness from Adversarial Human Attack](https://mlsanity.com/paper/1908.06083/) (2019)
- [The Design and Implementation of XiaoIce, an Empathetic Social Chatbot](https://mlsanity.com/paper/1812.08989/) (2018)
- [Neural Approaches to Conversational AI](https://mlsanity.com/paper/1809.08267/) (2018)
- [Constructing Unrestricted Adversarial Examples with Generative Models](https://mlsanity.com/paper/1805.07894/) (2018)
- [Generating Informative and Diverse Conversational Responses via Adversarial Information Maximization](https://mlsanity.com/paper/1809.05972/) (2018)
- [Towards an Automatic Turing Test: Learning to Evaluate Dialogue Responses](https://mlsanity.com/paper/1708.07149/) (2017)
- [SemanticAdv: Generating Adversarial Examples via Attribute-conditional Image Editing](https://mlsanity.com/paper/1906.07927/) (2019)
- [Human-centric Dialog Training via Offline Reinforcement Learning](https://mlsanity.com/paper/2010.05848/) (2020)
- [Dialogue Response Ranking Training with Large-Scale Human Feedback Data](https://mlsanity.com/paper/2009.06978/) (2020)
- [UNION: An Unreferenced Metric for Evaluating Open-ended Story Generation](https://mlsanity.com/paper/2009.07602/) (2020)
- [Unrestricted Adversarial Examples](https://mlsanity.com/paper/1809.08352/) (2018)
- [Re-evaluating ADEM: A Deeper Look at Scoring Dialogue Responses](https://mlsanity.com/paper/1902.08832/) (2019)
- [AT-GAN: An Adversarial Generator Model for Non-constrained Adversarial Examples](https://mlsanity.com/paper/1904.07793/) (2019)

## Built on by (most cited first, 2 of 2)

- [Probing the Robustness of Trained Metrics for Conversational Dialogue Systems](https://mlsanity.com/paper/2202.13887/) (2022)
- [The Label Imitation Game: Turing Test Network for Zero-Shot Pseudo-Label Pruning](https://mlsanity.com/paper/2606.30875/) (2026)

## Abstract (arXiv)

The design of better automated dialogue evaluation metrics offers the potential of accelerate evaluation research on conversational AI. However, existing trainable dialogue evaluation models are generally restricted to classifiers trained in a purely supervised manner, which suffer a significant risk from adversarial attacking (e.g., a nonsensical response that enjoys a high classification score). To alleviate this risk, we propose an adversarial training approach to learn a robust model, ATT (Adversarial Turing Test), that discriminates machine-generated responses from human-written replies. In contrast to previous perturbation-based methods, our discriminator is trained by iteratively generating unrestricted and diverse adversarial examples using reinforcement learning. The key benefit of this unrestricted adversarial training approach is allowing the discriminator to improve robustness in an iterative attack-defense game. Our discriminator shows high accuracy on strong attackers including DialoGPT and GPT-3.