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

Get Ready for the ISDA Notices Hub

No one wants to have to terminate a derivatives trading relationship – that usually means a counterparty has failed to make a payment or has become insolvent. At an already stressful time, the last thing anyone needs is to experience...

ISDA Publishes Paper on SFDR Review

On June 23, ISDA and the Association for Financial Markets in Europe (AFME) published a position paper on the review of the Sustainable Finance Disclosure Regulation (SFDR). The paper acknowledges that the SFDR needs to be revised in line with...