arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2503.02776cs.CLcs.AI
收藏

LLMs中的隐式偏见:一项综述

Implicit Bias in LLMs: A Survey

Beijing Foreign Studies University(北京外国语大学)

Xinru Lin, Luyang Li

AI总结:

本文综述了LLMs中的隐式偏见研究,借鉴心理学概念将检测方法分为词汇联想、文本生成和决策制定,并分类评估指标与数据集,总结缓解努力以指导未来研究。

摘要:

由于开发者实施了护栏,大型语言模型(LLMs)在显式偏见测试中表现出色。然而,LLMs中的偏见可能不仅显式存在,也可能隐式存在,就像人类有意识地追求公正却仍怀有隐式偏见一样。隐式偏见的无意识和自动特性使其研究尤为困难。本文对LLMs中隐式偏见的现有文献进行了全面综述。我们首先介绍了心理学中与隐式偏见相关的关键概念、理论和方法,并将其从人类扩展到LLMs。借鉴内隐联想测验(IAT)及其他心理学框架,我们将检测方法分为三种主要途径:词汇联想、面向任务的文本生成和决策制定。我们将隐式偏见的评估指标分类体系分为两类:基于单值的指标和基于比较值的指标。我们将数据集分为两类:带掩码标记的句子和完整句子,并纳入了来自不同领域的数据集,以反映LLMs的广泛应用。尽管缓解LLMs中隐式偏见的研究仍然有限,我们仍总结了现有努力,并提供了对未来挑战的见解。我们希望这项工作能为研究人员提供清晰的指导,并激发创新想法以推进该任务的探索。

英文摘要:

Due to the implement of guardrails by developers, Large language models (LLMs) have demonstrated exceptional performance in explicit bias tests. However, bias in LLMs may occur not only explicitly, but also implicitly, much like humans who consciously strive for impartiality yet still harbor implicit bias. The unconscious and automatic nature of implicit bias makes it particularly challenging to study. This paper provides a comprehensive review of the existing literature on implicit bias in LLMs. We begin by introducing key concepts, theories and methods related to implicit bias in psychology, extending them from humans to LLMs. Drawing on the Implicit Association Test (IAT) and other psychological frameworks, we categorize detection methods into three primary approaches: word association, task-oriented text generation and decision-making. We divide our taxonomy of evaluation metrics for implicit bias into two categories: single-value-based metrics and comparison-value-based metrics. We classify datasets into two types: sentences with masked tokens and complete sentences, incorporating datasets from various domains to reflect the broad application of LLMs. Although research on mitigating implicit bias in LLMs is still limited, we summarize existing efforts and offer insights on future challenges. We aim for this work to serve as a clear guide for researchers and inspire innovative ideas to advance exploration in this task.

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。

↑