用微调版GPT-4o-mini高效识别教育数据中的敏感信息，准确率超95%且成本低。
Enhancing the De-identification of Personally Identifiable Information in Educational Data
- 微调GPT-4o-mini模型，提升对姓名等敏感信息的识别能力。
- 在CRAPII数据集上召回率达0.9589，精度提升三倍，计算成本降为十分之一。
- 跨文化、跨性别表现稳定，仅需少量新数据即可适配新场景。
保护学习技术中的个人可识别信息（PII），如姓名，是保障师生隐私与维持信任的关键。准确检测PII是匿名化敏感信息并保留教育数据价值的重要步骤。受人工智能进展启发，本研究探索了成本低廉且高效的GPT-4o-mini模型在PII检测任务中的应用。我们比较了提示工程与微调两种方法，并将其性能与Microsoft Presidio和Azure AI Language框架对比。在两个公开数据集CRAPII和TSCC上的评估表明，微调后的GPT-4o-mini在CRAPII上达到0.9589的召回率；同时精度显著提升（三倍增长），计算成本降至Azure AI Language的约十分之一。偏见分析显示，该模型在不同文化背景和性别下均保持高准确性。基于TSCC数据集的泛化分析进一步证明其鲁棒性，在仅使用少量新增训练数据的情况下，召回率高达0.9895。结果表明，微调后的GPT-4o-mini可作为精准且低成本的教育数据PII检测工具，兼顾隐私保护与数据可用性。代码已开源：https://github.com/AnonJD/PrivacyAI。
原文摘要 · Abstract (English)
Protecting Personally Identifiable Information (PII), such as names, is a critical requirement in learning technologies to safeguard student and teacher privacy and maintain trust. Accurate PII detection is an essential step toward anonymizing sensitive information while preserving the utility of educational data. Motivated by recent advancements in artificial intelligence, our study investigates the GPT-4o-mini model as a cost-effective and efficient solution for PII detection tasks. We explore both prompting and fine-tuning approaches and compare GPT-4o-mini's performance against established frameworks, including Microsoft Presidio and Azure AI Language. Our evaluation on two public datasets, CRAPII and TSCC, demonstrates that the fine-tuned GPT-4o-mini model achieves superior performance, with a recall of 0.9589 on CRAPII. Additionally, fine-tuned GPT-4o-mini significantly improves precision scores (a threefold increase) while reducing computational costs to nearly one-tenth of those associated with Azure AI Language. Furthermore, our bias analysis reveals that the fine-tuned GPT-4o-mini model consistently delivers accurate results across diverse cultural backgrounds and genders. The generalizability analysis using the TSCC dataset further highlights its robustness, achieving a recall of 0.9895 with minimal additional training data from TSCC. These results emphasize the potential of fine-tuned GPT-4o-mini as an accurate and cost-effective tool for PII detection in educational data. It offers robust privacy protection while preserving the data's utility for research and pedagogical analysis. Our code is available on GitHub: https://github.com/AnonJD/PrivacyAI
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。