# "Nice Try, Kiddo": Investigating Ad Hominems in Dialogue Responses

arXiv: https://arxiv.org/abs/2010.12820 · HTML: https://mlsanity.com/paper/2010.12820/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Oct 2020.

## Built on by (most cited first, 3 of 3)

- [Generating Syntactically Controlled Paraphrases without Using Annotated Parallel Pairs](https://mlsanity.com/paper/2101.10579/) (2021)
- [Controllable Text Generation for Open-Domain Creativity and Fairness](https://mlsanity.com/paper/2209.12099/) (2022)
- ["Dummy Grandpa, do you know anything?": Identifying and Characterizing Ad hominem Fallacy Usage in the Wild](https://mlsanity.com/paper/2209.02062/) (2022)

## Abstract (arXiv)

Ad hominem attacks are those that target some feature of a person's character instead of the position the person is maintaining. These attacks are harmful because they propagate implicit biases and diminish a person's credibility. Since dialogue systems respond directly to user input, it is important to study ad hominems in dialogue responses. To this end, we propose categories of ad hominems, compose an annotated dataset, and build a classifier to analyze human and dialogue system responses to English Twitter posts. We specifically compare responses to Twitter topics about marginalized communities (#BlackLivesMatter, #MeToo) versus other topics (#Vegan, #WFH), because the abusive language of ad hominems could further amplify the skew of power away from marginalized populations. Furthermore, we propose a constrained decoding technique that uses salient n-gram similarity as a soft constraint for top-k sampling to reduce the amount of ad hominems generated. Our results indicate that 1) responses from both humans and DialoGPT contain more ad hominems for discussions around marginalized communities, 2) different quantities of ad hominems in the training data can influence the likelihood of generating ad hominems, and 3) we can use constrained decoding techniques to reduce ad hominems in generated dialogue responses.