# Probing the Robustness of Trained Metrics for Conversational Dialogue Systems

arXiv: https://arxiv.org/abs/2202.13887 · HTML: https://mlsanity.com/paper/2202.13887/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 19 references that are in the map.
- First posted on arXiv 28 Feb 2022.

## Builds on (most cited first, 15 of 15)

- [Personalizing Dialogue Agents: I have a dog, do you have pets too?](https://mlsanity.com/paper/1801.07243/) (2018)
- [DailyDialog: A Manually Labelled Multi-turn Dialogue Dataset](https://mlsanity.com/paper/1710.03957/) (2017)
- [Recipes for building an open-domain chatbot](https://mlsanity.com/paper/2004.13637/) (2020)
- [How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation](https://mlsanity.com/paper/1603.08023/) (2016)
- [Why We Need New Evaluation Metrics for NLG](https://mlsanity.com/paper/1707.06875/) (2017)
- [USR: An Unsupervised and Reference Free Evaluation Metric for Dialog Generation](https://mlsanity.com/paper/2005.00456/) (2020)
- [The Second Conversational Intelligence Challenge (ConvAI2)](https://mlsanity.com/paper/1902.00098/) (2019)
- [Survey on Evaluation Methods for Dialogue Systems](https://mlsanity.com/paper/1905.04071/) (2019)
- [Towards an Automatic Turing Test: Learning to Evaluate Dialogue Responses](https://mlsanity.com/paper/1708.07149/) (2017)
- [A Comprehensive Assessment of Dialog Evaluation Metrics](https://mlsanity.com/paper/2106.03706/) (2021)
- [RUBER: An Unsupervised Method for Automatic Evaluation of Open-Domain Dialog Systems](https://mlsanity.com/paper/1701.03079/) (2017)
- [Learning an Unreferenced Metric for Online Dialogue Evaluation](https://mlsanity.com/paper/2005.00583/) (2020)
- [Re-evaluating ADEM: A Deeper Look at Scoring Dialogue Responses](https://mlsanity.com/paper/1902.08832/) (2019)
- [Towards a Metric for Automated Conversational Dialogue System Evaluation and Improvement](https://mlsanity.com/paper/1909.12066/) (2019)
- [An Adversarially-Learned Turing Test for Dialog Generation Models](https://mlsanity.com/paper/2104.08231/) (2021)

## Built on by (most cited first, 6 of 6)

- [Report from the NSF Future Directions Workshop on Automatic Evaluation of Dialog: Research Directions and Challenges](https://mlsanity.com/paper/2203.10012/) (2022)
- [Text Style Transfer Evaluation Using Large Language Models](https://mlsanity.com/paper/2308.13577/) (2023)
- [Don't Forget Your ABC's: Evaluating the State-of-the-Art in Chat-Oriented Dialogue Systems](https://mlsanity.com/paper/2212.09180/) (2022)
- [A RAG-Based Multi-Agent LLM System for Natural Hazard Resilience and Adaptation](https://mlsanity.com/paper/2504.17200/) (2025)
- [Favi-Score: A Measure for Favoritism in Automated Preference Ratings for Generative AI Evaluation](https://mlsanity.com/paper/2406.01131/) (2024)
- [Exploring the Impact of Human Evaluator Group on Chat-Oriented Dialogue Evaluation](https://mlsanity.com/paper/2309.07998/) (2023)

## Abstract (arXiv)

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.