Benchmarking Generative AI for CSA Clause Extraction and CDM Representation

This whitepaper explores recent advances in generative artificial intelligence (AI) and its potential to automate the extraction, interpretation and digitization of legal clauses from ISDA’s credit support annexes (CSAs) into standardized, machine-readable code using the Common Domain Model (CDM). Specifically, the paper benchmarks and reviews the ability of generative AI to accurately extract five CSA clauses and digitize them into CDM format. The findings suggest that integrating industry-specific data significantly boosts generative AI accuracy, larger generative AI models typically handle nuanced legal language better, and generative AI can be utilized within a modular framework (eg,agentic AI) to extract legal clauses more accurately and efficiently.

Click on the attached PDF to read the full report.

Documents (1) for Benchmarking Generative AI for CSA Clause Extraction and CDM Representation

Launch of ISDA Notices Hub and Protocol

ISDA has launched the ISDA Notices Hub and the ISDA 2025 Notices Hub Protocol, giving users a faster and more efficient method for delivering critical notices and reducing the uncertainty and risk of losses that can result from delays. The...

ISDA response to ESMA MiFIR Review Consultation

On July 11, ISDA submitted a response to the European Securities and Markets Authority's (ESMA) fourth package of Level 2 consultation under the Markets in Financial Instruments Regulation Review (MiFIR), on transparency for derivatives, package orders and input/output data for...