Ser-Huang Poon (Alliance Manchester Business) et al. have posted “Analysing Modern Slavery Statements (MSS) Using Large Language Models (LLMs)” (AI & Higher Education Handbook, Edward Elgar Publishing, 2025.) on SSRN. Here is the abstract:
This chapter explores the application of Large Language Models (LLMs) to analyse Modern Slavery Statements (MSS). As businesses are increasingly required to produce MSS to comply with legislation, the volume of these documents presents challenges in monitoring and evaluation. LLMs offer a scalable solution for extracting, classifying, and assessing the content of MSS, enabling organisations and regulators to identify compliance issues and patterns of modern slavery risks. By leveraging LLMs, the analysis can go beyond simple keyword searches to understand the context and nuances within MSS, offering a more comprehensive insight into corporate responses to modern slavery. This chapter demonstrates the potential of LLMs to enhance transparency and accountability in corporate reporting on human rights issues, particularly in addressing modern slavery.