通过定制化偏见模型，让大模型对话更包容多元视角。
Capturing Bias Diversity in LLMs
- 构建多个带特定偏见的GPT实例，模拟不同人群观点。
- 多模型协作生成整合响应，覆盖性别、年龄、种族等多样性。
- 适合关注公平性与包容性的AI开发者和研究者。
本文研究通过在大语言模型（LLMs）输出中引入多样性，提升其表现。我们提出一种由多个定制化GPT模型组成的配置，展示单一模型可承载的偏见多样性。通过开发多个反映特定人口特征（如性别、年龄、种族）偏见的GPT实例，我们构建并评估了一个名为BiasGPT的框架，旨在实现更细腻、更具代表性的智能对话。这些定制模型将协同工作，将不同视角融合为综合回应，捕捉广泛的人类经验与观点。实验表明，单个GPT模型可嵌入多种偏见，当它们结合时，有望推动更具包容性的AI技术发展。
原文摘要 · Abstract (English)
This paper presents research on enhancements to Large Language Models (LLMs) through the addition of diversity in its generated outputs. Our study introduces a configuration of multiple LLMs which demonstrates the diversities capable with a single LLM. By developing multiple customised instances of a GPT model, each reflecting biases in specific demographic characteristics including gender, age, and race, we propose, develop and evaluate a framework for a more nuanced and representative AI dialogue which we call BiasGPT. The customised GPT models will ultimately collaborate, merging their diverse perspectives on a topic into an integrated response that captures a broad spectrum of human experiences and viewpoints. In this paper, through experiments, we demonstrate the capabilities of a GPT model to embed different biases which, when combined, can open the possibilities of more inclusive AI technologies.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。