2021/04/16 by Xiang Gao, Yizhe Zhang, Gao, Xiang +5
Computer Science · #Adversarial Robustness in Machine Learning #Computation and Language (cs.CL) #FOS: Computer and information sciences #Hate Speech and Cyberbullying Detection #Topic Modeling #cs.CL
paper · pdf · doi:10.48550/arxiv.2104.08231
7 pages, 2 figures
arxiv created 2021/04/16 · openalex publication_date 2021/04/16 · arxiv updated 2021/04/19 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
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.