Related papers: Revealing Persona Biases in Dialogue Systems

Revealing Persona Biases in Dialogue Systems

URL: http://arxiv.org/abs/2104.08728v1
Date: Sun, 18 Apr 2021 05:44:41 GMT
Title: Revealing Persona Biases in Dialogue Systems
Authors: Emily Sheng, Josh Arnold, Zhou Yu, Kai-Wei Chang, Nanyun Peng
Abstract summary: We present the first large-scale study on persona biases in dialogue systems. We conduct analyses on personas of different social classes, sexual orientations, races, and genders. 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.
Score: 64.96908171646808
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: 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.

Related papers

From Pixels to Personas: Investigating and Modeling Self-Anthropomorphism in Human-Robot Dialogues [29.549159419088294]
Self-anthropomorphism in robots manifests itself through their display of human-like characteristics in dialogue, such as expressing preferences and emotions. We show significant differences in these two types of responses and propose transitioning from one type to the other. We introduce Pix2Persona, a novel dataset aimed at developing ethical and engaging AI systems in various embodiments.
arXiv Detail & Related papers (2024-10-04T19:06:24Z)
Personality-affected Emotion Generation in Dialog Systems [67.40609683389947]
We propose a new task, Personality-affected Emotion Generation, to generate emotion based on the personality given to the dialog system. We analyze the challenges in this task, i.e., (1) heterogeneously integrating personality and emotional factors and (2) extracting multi-granularity emotional information in the dialog context. Results suggest that by adopting our method, the emotion generation performance is improved by 13% in macro-F1 and 5% in weighted-F1 from the BERT-base model.
arXiv Detail & Related papers (2024-04-03T08:48:50Z)
Are Personalized Stochastic Parrots More Dangerous? Evaluating Persona Biases in Dialogue Systems [103.416202777731]
We study "persona biases", which we define to be the sensitivity of dialogue models' harmful behaviors contingent upon the personas they adopt. We categorize persona biases into biases in harmful expression and harmful agreement, and establish a comprehensive evaluation framework to measure persona biases in five aspects: Offensiveness, Toxic Continuation, Regard, Stereotype Agreement, and Toxic Agreement.
arXiv Detail & Related papers (2023-10-08T21:03:18Z)
Mirages: On Anthropomorphism in Dialogue Systems [12.507948345088135]
We discuss the linguistic factors that contribute to the anthropomorphism of dialogue systems and the harms that can arise. We recommend that future efforts towards developing dialogue systems take particular care in their design, development, release, and description.
arXiv Detail & Related papers (2023-05-16T20:50:46Z)
Robots-Dont-Cry: Understanding Falsely Anthropomorphic Utterances in Dialog Systems [64.10696852552103]
Highly anthropomorphic responses might make users uncomfortable or implicitly deceive them into thinking they are interacting with a human. We collect human ratings on the feasibility of approximately 900 two-turn dialogs sampled from 9 diverse data sources.
arXiv Detail & Related papers (2022-10-22T12:10:44Z)
Understanding How People Rate Their Conversations [73.17730062864314]
We conduct a study to better understand how people rate their interactions with conversational agents. We focus on agreeableness and extraversion as variables that may explain variation in ratings.
arXiv Detail & Related papers (2022-06-01T00:45:32Z)
Less is More: Learning to Refine Dialogue History for Personalized Dialogue Generation [57.73547958927826]
We propose to refine the user dialogue history on a large scale, based on which we can handle more dialogue history and obtain more accurate persona information. Specifically, we design an MSP model which consists of three personal information refiners and a personalized response generator.
arXiv Detail & Related papers (2022-04-18T02:02:56Z)
Towards Building a Personalized Dialogue Generator via Implicit User Persona Detection [0.0]
We consider high-quality transmission is essentially built based on apprehending the persona of the other party. Motivated by this, we propose a novel personalized dialogue generator by detecting implicit user persona.
arXiv Detail & Related papers (2022-04-15T08:12:10Z)
Mitigating Gender Bias for Neural Dialogue Generation with Adversarial Learning [44.69720475052093]
We propose a novel adversarial learning framework Debiased-Chat to train dialogue models free from gender bias. Our framework significantly reduces gender bias in dialogue models while maintaining the response quality.
arXiv Detail & Related papers (2020-09-28T02:46:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.