Recent advancements in Large Language Models empower them to follow freeform
instructions, including imitating generic or specific demographic personas in
conversations. Generic personas refer to an individual from a demographic group
(e.g. an Asian person), whereas specific personas can be actual names of
historical figures. While the adoption of personas allows dialogue systems to
be more engaging and approachable to users, it also carries the potential risk
of exacerbating social biases in model responses, further causing societal
harms through interactions with users. In this paper, we systematically study
"persona biases", which we define to be the sensitivity of harmful dialogue
model behaviors to different persona adoptions. We categorize persona biases
into biases in harmful expression and harmful agreement, as well as establish a
comprehensive evaluation framework to measure persona biases in five aspects:
Offensiveness, Toxic Continuation, Regard, Stereotype Agreement, and Toxic
Agreement. Additionally, we propose to comprehensively investigate persona
biases through experimenting with UniversalPersona, a systematized persona
dataset with a comprehensive list of both generic and specific model personas.
Through benchmarking on four different models, including Blender, ChatGPT,
Alpaca, and Vicuna, our study uncovers significant persona biases in these
dialogue systems.Findings of our study underscores the immediate need to
revisit the use of persona traits in dialogue agents, to ensure their safe
application.

最近在大型语言模型的突破使它们能够遵循自由格式的指令，其中包括模仿对话中一般或特定人口群体。本文系统研究了 “人物偏见”，将其定义为对不同人物采用敏感有害的对话模型行为的问题。我们将人物偏见分为有害表达和有害协议的偏见，并建立了一个全面的评估框架，以衡量人物偏见的五个方面：冒犯性、毒性，关注度，刻板协议和有害协议。此外，我们建议通过对通用人物数据集进行全面调查，该数据集包含全面的一般和特定模型人物列表，从而全面研究人物偏见。通过对包括 Blender、ChatGPT、Alpaca 和 Vicuna 在内的四个不同模型进行基准测试，我们的研究揭示了这些对话系统中显著的人物偏见。我们的研究结果强调了重新审视人物特点在对话代理程序中的使用的迫切需求，以确保其安全应用。

评估对话系统中的个体偏差：个性化的随机鹦鹉是否更危险？

Are Personalized Stochastic Parrots More Dangerous? Evaluating Persona  Biases in Dialogue Systems

Dialogue systems in the form of chatbots and personal assistants are being
increasingly integrated into people's lives. Modern dialogue systems may
consider adopting anthropomorphic personas, mimicking societal demographic
groups to appear more approachable and trustworthy to users. However, the
adoption of a persona can result in the adoption of biases. 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. We define persona biases as harmful differences in
responses (e.g., varying levels of offensiveness, agreement with harmful
statements) generated from adopting different demographic personas.
Furthermore, we introduce an open-source framework, UnitPersonaBias, to explore
and aggregate persona biases in dialogue systems. By analyzing the Blender and
DialoGPT dialogue systems, we observe that adopting personas can actually
decrease harmful responses, compared to not using any personas. Additionally,
we find that persona choices can affect the degree of harms in generated
responses and thus should be systematically evaluated before deployment. We
also analyze how personas can result in different amounts of harm towards
specific demographics.

本文研究了对话系统的人格偏见，并分析了不同社会阶级、性取向、种族和性别的人物角色。研究者提出将对话系统的角色升级到拥有更多人文特征以更好的迎合用户的趋势可能会产生一些偏见。他们还介绍了一个开源框架 UnitPersonaBias，以探索和聚合对话系统中的人格偏见。此外，研究者还发现与不使用人格形象相比，采用人格形象可能会减少有害的回应。但是，人格选择会影响生成响应中危害程度，因此在实际应用前应该进行系统评估。