REFINE-LM：通过强化学习缓解语言模型刻板印象
REFINE-LM: Mitigating Language Model Stereotypes via Reinforcement Learning
AI总结：
针对语言模型存在的多类刻板印象偏差问题，提出无需微调、标注少、成本低的REFINE-LM强化学习去偏方法，可在保留模型性能的同时有效降低多类偏差。
摘要：
随着（大）语言模型的推出，人们对这类模型可能从训练数据中继承的意外偏差产生了极大担忧。大量研究表明，这类模型会传播性别刻板印象，以及地理和种族偏差等多种偏差。现有研究通过数据预处理和嵌入去偏来解决该问题，但所提方法需要大量计算资源和标注工作，且仅局限于特定类型的偏差。为解决这些问题，我们提出REFINE-LM，这是一种无需任何微调即可利用强化学习处理不同类型偏差的去偏方法。通过在语言模型的词概率分布之上训练一个简单模型，我们的偏差无关强化学习方法无需人工标注或大量计算资源即可实现模型去偏。在包括多个语言模型在内的广泛模型上开展的实验表明，我们的方法（i）在保留语言模型性能的同时显著降低了刻板印象偏差；（ii）适用于不同类型的偏差，可在性别、种族、宗教和国籍类偏差等场景中泛化；（iii）训练成本不高。
英文摘要：
With the introduction of (large) language models, there has been significant concern about the unintended bias such models may inherit from their training data. A number of studies have shown that such models propagate gender stereotypes, as well as geographical and racial bias, among other biases. While existing works tackle this issue by preprocessing data and debiasing embeddings, the proposed methods require a lot of computational resources and annotation effort while being limited to certain types of biases. To address these issues, we introduce REFINE-LM, a debiasing method that uses reinforcement learning to handle different types of biases without any fine-tuning. By training a simple model on top of the word probability distribution of a LM, our bias agnostic reinforcement learning method enables model debiasing without human annotations or significant computational resources. Experiments conducted on a wide range of models, including several LMs, show that our method (i) significantly reduces stereotypical biases while preserving LMs performance; (ii) is applicable to different types of biases, generalizing across contexts such as gender, ethnicity, religion, and nationality-based biases; and (iii) it is not expensive to train.
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。
