De-identifying student personally identifying information in discussion forum posts with large language models

Academic Paper
Written By Michael Wiemeyer

This study aims to evaluate the effectiveness of three large language models (LLMs), GPT-4o, Llama 3.3 70B and Llama 3.1 8B, in redacting personally identifying information (PII) from forum data in massive open online courses (MOOCs).

See the Resource

Michael Wiemeyer
Previous

Can A Language Model Represent Math Strategies?”: Learning Math Strategies from Big Data using BERT
Next

De-identifying Student Personally Identifying Information with GPT-4