paper-with-me

홈 › Papers

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

2023-10-08 · Yixin Wan, Jieyu Zhao, Aman Chadha, Nanyun Peng, Kai-Wei Chang

Recent advancements in Large Language Models empower them to follow freeform instructions, including imitating generic or specific demographic personas in conversations. We define generic personas to represent demographic groups, such as "an Asian person", whereas specific personas may take the form of specific popular Asian names like "Yumi". While the adoption of personas enriches user experiences by making dialogue systems more engaging and approachable, it also casts a shadow of potential risk by exacerbating social biases within model responses, thereby causing societal harm through interactions with users. In this paper, we systematically 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. Additionally, we propose to investigate persona biases by experimenting with UNIVERSALPERSONA, a systematically constructed persona dataset encompassing various types 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 dialogue systems. Our findings also underscore the pressing need to revisit the use of personas in dialogue agents to ensure safe application.

📄 PDF Abstract BibTeX arXiv:2310.05280

Code (1)

uclanlp/persona-biases 공식 구현 pytorch

Tasks

Benchmarking

Methods 이 논문이 사용한 방법론

RoIPool 설명 없음
RoIAlign Region of Interest Align, or RoIAlign, is an operation for extracting a small feature map from each RoI in detection and segmentation based tasks. It removes the harsh…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Similar Papers 제목 키워드 기반

The Dark Side of ChatGPT: Legal and Ethical Challenges from Stochastic Parrots and Hallucination

2023-04-21 · Zihao Li

With the launch of ChatGPT, Large Language Models (LLMs) are shaking up our whole society, rapidly altering the way we think, create and live. For instance, the GPT integration in Bing has altered our approach to online …

Hallucination

The Slodderwetenschap (Sloppy Science) of Stochastic Parrots -- A Plea for Science to NOT take the Route Advocated by Gebru and Bender

2021-01-11 · Michael Lissack

This article is a position paper written in reaction to the now-infamous paper titled "On the Dangers of Stochastic Parrots: Can Language Models Be Too Big?" by Timnit Gebru, Emily Bender, and others who were, as of the …

EthicsPosition

Playing games with Large language models: Randomness and strategy

2025-03-04 · Alicia Vidler, Toby Walsh

Playing games has a long history of describing intricate interactions in simplified forms. In this paper we explore if large language models (LLMs) can play games, investigating their capabilities for randomisation and s…

Flocks of Stochastic Parrots: Differentially Private Prompt Learning for Large Language Models

2023-05-24 · NeurIPS 2023 11

Large language models (LLMs) are excellent in-context learners. However, the sensitivity of data contained in prompts raises privacy concerns. Our work first shows that these concerns are valid: we instantiate a simple b…

Inference AttackMembership Inference AttackPrompt Learningvalid

Causal Parrots: Large Language Models May Talk Causality But Are Not Causal

2023-08-24 · Matej Zečević, Moritz Willig, Devendra Singh Dhami, Kristian Kersting

Some argue scale is all what is needed to achieve AI, covering even causal models. We make it clear that large language models (LLMs) cannot be causal and give reason onto why sometimes we might feel otherwise. To this e…

Causal Inference