Towards Human-Centered RegTech: Unpacking Professionals' Strategies and Needs for Using LLMs Safely
This addresses compliance challenges for professionals in law, healthcare, and finance using LLMs, but is incremental as it identifies gaps rather than solving them.
The study investigated compliance risks when professionals use Large Language Models in high-risk domains, finding that experts are concerned about information leakage and output quality, and that their spontaneous mitigation strategies are limited due to lack of guidance.
Large Language Models are profoundly changing work patterns in high-risk professional domains, yet their application also introduces severe and underexplored compliance risks. To investigate this issue, we conducted semi-structured interviews with 24 highly-skilled knowledge workers from industries such as law, healthcare, and finance. The study found that these experts are commonly concerned about sensitive information leakage, intellectual property infringement, and uncertainty regarding the quality of model outputs. In response, they spontaneously adopt various mitigation strategies, such as actively distorting input data and limiting the details in their prompts. However, the effectiveness of these spontaneous efforts is limited due to a lack of specific compliance guidance and training for Large Language Models. Our research reveals a significant gap between current NLP tools and the actual compliance needs of experts. This paper positions these valuable empirical findings as foundational work for building the next generation of Human-Centered, Compliance-Driven Natural Language Processing for Regulatory Technology (RegTech), providing a critical human-centered perspective and design requirements for engineering NLP systems that can proactively support expert compliance workflows.