# A Crowd-based Evaluation of Abuse Response Strategies in Conversational Agents

arXiv: https://arxiv.org/abs/1909.04387 · HTML: https://mlsanity.com/paper/1909.04387/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Sep 2019.

## Built on by (most cited first, 12 of 12)

- [ToxicChat: Unveiling Hidden Challenges of Toxicity Detection in Real-World User-AI Conversation](https://mlsanity.com/paper/2310.17389/) (2023)
- [Anticipating Safety Issues in E2E Conversational AI: Framework and Tooling](https://mlsanity.com/paper/2107.03451/) (2021)
- [ConvAbuse: Data, Analysis, and Benchmarks for Nuanced Abuse Detection in Conversational AI](https://mlsanity.com/paper/2109.09483/) (2021)
- [SaFeRDialogues: Taking Feedback Gracefully after Conversational Safety Failures](https://mlsanity.com/paper/2110.07518/) (2021)
- [Assessing Political Prudence of Open-domain Chatbots](https://mlsanity.com/paper/2106.06157/) (2021)
- [EmoWOZ: A Large-Scale Corpus and Labelling Scheme for Emotion Recognition in Task-Oriented Dialogue Systems](https://mlsanity.com/paper/2109.04919/) (2021)
- [Alexa, Google, Siri: What are Your Pronouns? Gender and Anthropomorphism in the Design and Perception of Conversational Assistants](https://mlsanity.com/paper/2106.02578/) (2021)
- ["Alexa doesn't have that many feelings": Children's understanding of AI through interactions with smart speakers in their homes](https://mlsanity.com/paper/2305.05597/) (2023)
- [Neural Generation Meets Real People: Building a Social, Informative Open-Domain Dialogue Agent](https://mlsanity.com/paper/2207.12021/) (2022)
- [Safer Conversational AI as a Source of User Delight](https://mlsanity.com/paper/2304.09865/) (2023)
- [It Couldn't Help But Overhear: On the Limits of Modelling Meta-Communicative Grounding Acts with Supervised Learning](https://mlsanity.com/paper/2405.01139/) (2024)
- [How AI Assistants Respond to Repeated Abuse](https://mlsanity.com/paper/2609.17547/) (2026)

## Abstract (arXiv)

How should conversational agents respond to verbal abuse through the user? To answer this question, we conduct a large-scale crowd-sourced evaluation of abuse response strategies employed by current state-of-the-art systems. Our results show that some strategies, such as "polite refusal" score highly across the board, while for other strategies demographic factors, such as age, as well as the severity of the preceding abuse influence the user's perception of which response is appropriate. In addition, we find that most data-driven models lag behind rule-based or commercial systems in terms of their perceived appropriateness.