Probing the Robustness of Trained Metrics for Conversational Dialogue Systems

2022/02/28 by Jan Deriu, Don Tuggener, Deriu, Jan +5
Computer Science · #AI in Service Interactions #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Speech and dialogue systems #Topic Modeling

paper · pdf · doi:10.48550/arxiv.2202.13887

openalex publication_date 2022/02/28 · openalex created_date 2022/04/03 · openalex updated_date 2026/08/01

Abstract

This paper introduces an adversarial method to stress-test trained metrics to evaluate conversational dialogue systems. The method leverages Reinforcement Learning to find response strategies that elicit optimal scores from the trained metrics. We apply our method to test recently proposed trained metrics. We find that they all are susceptible to giving high scores to responses generated by relatively simple and obviously flawed strategies that our method converges on. For instance, simply copying parts of the conversation context to form a response yields competitive scores or even outperforms responses written by humans.

Related

• Learning from Real Users: Rating Dialogue Success with Neural Networks for Reinforcement Learning in Spoken Dialogue Systems
• Measuring the Robustness of Reference-Free Dialogue Evaluation Systems
• An Adversarially-Learned Turing Test for Dialog Generation Models
• Dialogue Generation: From Imitation Learning to Inverse Reinforcement Learning
• Adversarial Learning for Neural Dialogue Generation