因果检验大语言模型中的性别偏见：职业偏见案例研究
Causally Testing Gender Bias in LLMs: A Case Study on Occupational Bias
AI总结：
本文提出衡量生成式语言模型偏见的因果框架与稳健基准设计原则，构建 OccuGender 评估 Llama、Mistral 等模型的职业性别偏见，并探讨提示缓解方法及框架泛化性。
摘要：
大语言模型（LLM）生成的文本已被证明会对各类人群表现出多种有害的、类似人类的偏见。这些发现推动了旨在理解和衡量此类效应的研究。本文提出了一种用于衡量生成式语言模型中偏见的因果表述。基于这一理论基础，我们列出了设计稳健偏见基准的若干期望条件。随后，我们提出了一个名为 OccuGender 的基准，并通过一套偏见衡量流程来调查职业性别偏见。我们在 OccuGender 上测试了多个最先进的开源 LLM，包括 Llama、Mistral 及其指令微调版本。结果表明，这些模型表现出显著的职业性别偏见。最后，我们讨论了用于缓解偏见的提示策略，以及对因果表述的扩展，以说明本框架的泛化能力。代码和数据位于 https://github.com/chenyuen0103/gender-bias。
英文摘要：
Generated texts from large language models (LLMs) have been shown to exhibit a variety of harmful, human-like biases against various demographics. These findings motivate research efforts aiming to understand and measure such effects. This paper introduces a causal formulation for bias measurement in generative language models. Based on this theoretical foundation, we outline a list of desiderata for designing robust bias benchmarks. We then propose a benchmark called OccuGender, with a bias-measuring procedure to investigate occupational gender bias. We test several state-of-the-art open-source LLMs on OccuGender, including Llama, Mistral, and their instruction-tuned versions. The results show that these models exhibit substantial occupational gender bias. Lastly, we discuss prompting strategies for bias mitigation and an extension of our causal formulation to illustrate the generalizability of our framework. Our code and data https://github.com/chenyuen0103/gender-bias.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
