Self Disclosure

Self-disclosure, the act of revealing personal information, is increasingly studied in the context of human-AI interactions, particularly with large language models (LLMs). Research focuses on understanding user behavior, including the types and frequency of disclosures, and developing methods to mitigate privacy risks associated with this information sharing, often employing machine learning models like BERT for detection and abstraction of sensitive details. These studies are crucial for improving the safety and ethical design of AI systems, informing the development of privacy-preserving technologies, and providing insights into human behavior in online environments.