arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2404.02650cs.LGcs.AIcs.CL
收藏

迈向检测大型语言模型中未预见的偏见

Towards detecting unanticipated bias in Large Language Models

Munich University of Applied Sciences(慕尼黑应用科学大学)

Anna Kruspe

AI总结:

针对大型语言模型中研究不足的隐性、未预见偏见,本文提出结合不确定性量化与可解释 AI 方法,评估决策确定性并揭示内部过程,以提升偏见检测能力与 AI 公平性、透明度。

摘要:

在过去一年中,像 ChatGPT 这样的大型语言模型(LLM)已得到广泛使用,并表现出与早期机器学习系统类似的公平性问题。当前研究主要集中于分析和量化训练数据中的这些偏见及其对模型决策的影响,同时制定缓解策略。这类研究大多针对与性别、种族、族裔和语言相关的众所周知的偏见。然而,LLM 显然还受到其他不太明显的隐性偏见影响。这些模型复杂且通常不透明的特性使检测此类偏见颇具挑战,但由于它们可能在各类应用中造成负面影响,做到这一点至关重要。本文探索检测 LLM 中这些未预见偏见的新途径,特别聚焦于不确定性量化(Uncertainty Quantification)和可解释人工智能(Explainable AI)方法。这些方法旨在评估模型决策的确定性,并使 LLM 的内部决策过程更加透明,从而识别和理解那些并非立即可见的偏见。通过本研究,我们致力于推动更公平、更透明的 AI 系统的发展。

英文摘要:

Over the last year, Large Language Models (LLMs) like ChatGPT have become widely available and have exhibited fairness issues similar to those in previous machine learning systems. Current research is primarily focused on analyzing and quantifying these biases in training data and their impact on the decisions of these models, alongside developing mitigation strategies. This research largely targets well-known biases related to gender, race, ethnicity, and language. However, it is clear that LLMs are also affected by other, less obvious implicit biases. The complex and often opaque nature of these models makes detecting such biases challenging, yet this is crucial due to their potential negative impact in various applications. In this paper, we explore new avenues for detecting these unanticipated biases in LLMs, focusing specifically on Uncertainty Quantification and Explainable AI methods. These approaches aim to assess the certainty of model decisions and to make the internal decision-making processes of LLMs more transparent, thereby identifying and understanding biases that are not immediately apparent. Through this research, we aim to contribute to the development of fairer and more transparent AI systems.

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。

↑