Revealing Persona Biases in Dialogue Systems

by   Emily Sheng, et al.

Dialogue systems in the form of chatbots and personal assistants are being increasingly integrated into people's lives. These dialogue systems often have the ability to adopt an anthropomorphic persona, mimicking a societal demographic to appear more approachable and trustworthy to users. However, the adoption of a persona can result in the adoption of biases. We define persona biases as harmful differences in text (e.g., varying levels of offensiveness or affirmations of biased statements) generated from adopting different demographic personas. In this paper, we present the first large-scale study on persona biases in dialogue systems and conduct analyses on personas of different social classes, sexual orientations, races, and genders. Furthermore, we introduce an open-source framework, UnitPersonaBias, a tool to explore and aggregate subtle persona biases in dialogue systems. In our studies of the Blender and DialoGPT dialogue systems, we show that the choice of personas can affect the degree of harms in generated responses. Additionally, adopting personas of more diverse, historically marginalized demographics appears to decrease harmful responses the most.


Towards Controllable Biases in Language Generation

We present a general approach towards controllable societal biases in na...

Mitigating Gender Bias for Neural Dialogue Generation with Adversarial Learning

Dialogue systems play an increasingly important role in various aspects ...

The Woman Worked as a Babysitter: On Biases in Language Generation

We present a systematic study of biases in natural language generation (...

An Equal-Size Hard EM Algorithm for Diverse Dialogue Generation

Open-domain dialogue systems aim to interact with humans through natural...

A Dialogue Concerning Two World Systems: Info-Computational vs. Mechanistic

The dialogue develops arguments for and against adopting a new world sys...

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

Ad hominem attacks are those that attack some feature of a person's char...

Strategy of the Negative Sampling for Training Retrieval-Based Dialogue Systems

The article describes the new approach for quality improvement of automa...