"Nice Try, Kiddo": Ad Hominems in Dialogue Systems

10/24/2020
by   Emily Sheng, et al.
0

Ad hominem attacks are those that attack some feature of a person's character instead of the position the person is maintaining. As a form of toxic and abusive language, ad hominems contain harmful language that could further amplify the skew of power inequality for marginalized populations. Since dialogue systems are designed to respond directly to user input, it is important to study ad hominems in these system responses. In this work, we propose categories of ad hominems that allow us to analyze human and dialogue system responses to Twitter posts. We specifically compare responses to Twitter posts about marginalized communities (#BlackLivesMatter, #MeToo) and other topics (#Vegan, #WFH). Furthermore, we propose a constrained decoding technique that uses salient n-gram similarity to apply soft constraints to top-k sampling and can decrease the amount of ad hominems generated by dialogue systems. Our results indicate that 1) responses composed by both humans and DialoGPT contain more ad hominems for discussions around marginalized communities versus other topics, 2) different amounts of ad hominems in the training data can influence the likelihood of the model generating ad hominems, and 3) we can thus carefully choose training data and use constrained decoding techniques to decrease the amount of ad hominems generated by dialogue systems.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/06/2020

Fact-based Dialogue Generation with Convergent and Divergent Decoding

Fact-based dialogue generation is a task of generating a human-like resp...
research
07/14/2021

Increasing Faithfulness in Knowledge-Grounded Dialogue with Controllable Features

Knowledge-grounded dialogue systems are intended to convey information t...
research
09/27/2020

Stylized Dialogue Response Generation Using Stylized Unpaired Texts

Generating stylized responses is essential to build intelligent and enga...
research
02/12/2023

Position Matters! Empirical Study of Order Effect in Knowledge-grounded Dialogue

With the power of large pretrained language models, various research wor...
research
04/18/2021

Revealing Persona Biases in Dialogue Systems

Dialogue systems in the form of chatbots and personal assistants are bei...
research
11/15/2022

Alzheimer's Dementia Detection through Spontaneous Dialogue with Proactive Robotic Listeners

As the aging of society continues to accelerate, Alzheimer's Disease (AD...

Please sign up or login with your details

Forgot password? Click here to reset