PBa-LLM：使用命名实体识别（NER）的隐私与偏见感知NLP
PBa-LLM: Privacy- and Bias-aware NLP using Named-Entity Recognition (NER)
AI总结：
针对LLM的隐私与偏见问题，提出基于NER匿名化和性别偏见减少的PBa-LLM框架，在简历评分场景中验证了性能保持与隐私保护效果。
摘要：
近年来，自然语言处理（NLP）在高风险人工智能应用中的使用显著增加，尤其是在大型语言模型（LLMs）出现之后。然而，尽管LLMs性能强大，它们也引入了重要的法律/伦理问题，特别是关于隐私、数据保护和透明度的问题。鉴于这些担忧，本研究探索使用命名实体识别（NER）来促进LLMs的隐私保护训练（或适配）。我们提出了一个框架，利用NER技术对文本数据中的敏感信息（如个人身份或地理位置）进行匿名化处理。为了衡量所提出的隐私保护学习框架在特定高风险和敏感场景（即基于AI的招聘流程简历评分）中对用户隐私和系统性能的影响，我们进行了评估。该研究涉及两个语言模型（BERT和RoBERTa）和六种匿名化算法（基于Presidio、FLAIR、BERT以及不同版本的GPT），应用于包含24,000份候选人档案的数据库。研究结果表明，所提出的隐私保护技术能有效维持系统性能，同时在保护候选人机密性方面发挥关键作用，从而在实验场景中促进信任。在提出的隐私保护方法之上，我们还实验应用了一种现有方法来减少LLMs中的性别偏见，最终获得了我们提出的隐私与偏见感知LLMs（PBa-LLMs）。请注意，所提出的PBa-LLMs已在特定场景（简历评分）中进行了评估，但通常适用于任何其他基于LLM的人工智能应用。
英文摘要：
The use of Natural Language Processing (NLP) in highstakes AI-based applications has increased significantly in recent years, especially since the emergence of Large Language Models (LLMs). However, despite their strong performance, LLMs introduce important legal/ ethical concerns, particularly regarding privacy, data protection, and transparency. Due to these concerns, this work explores the use of Named- Entity Recognition (NER) to facilitate the privacy-preserving training (or adaptation) of LLMs. We propose a framework that uses NER technologies to anonymize sensitive information in text data, such as personal identities or geographic locations. An evaluation of the proposed privacy-preserving learning framework was conducted to measure its impact on user privacy and system performance in a particular high-stakes and sensitive setup: AI-based resume scoring for recruitment processes. The study involved two language models (BERT and RoBERTa) and six anonymization algorithms (based on Presidio, FLAIR, BERT, and different versions of GPT) applied to a database of 24,000 candidate profiles. The findings indicate that the proposed privacy preservation techniques effectively maintain system performance while playing a critical role in safeguarding candidate confidentiality, thus promoting trust in the experimented scenario. On top of the proposed privacy-preserving approach, we also experiment applying an existing approach that reduces the gender bias in LLMs, thus finally obtaining our proposed Privacyand Bias-aware LLMs (PBa-LLMs). Note that the proposed PBa-LLMs have been evaluated in a particular setup (resume scoring), but are generally applicable to any other LLM-based AI application.
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。
