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
Latest
Bulk Adherence Upload Page
Please download the attached Excel worksheet and fill out a separate row for each adherence. Then select and upload your completed file using the buttons below. If any errors are found, please correct and re-upload. Note that, if the only...
ISDA In Review – May 2025
A compendium of links to new documents, research papers, press releases and comment letters published by ISDA in May 2025.
ISDA Response to HMT SI on Digital Assets
On May 23, ISDA sent a comment letter in response to a draft statutory instrument (SI) from His Majesty’s Treasury (HMT) that establishes a new regulatory framework for digital assets. In the letter, ISDA recommends a review of the proposed...
FX Emerging Markets Documentation
ISDA now hosts the Template Terms published by EMTA, Inc. (the Emerging Markets Traders Association). More information about ISDA’s and EMTA’s respective roles in documentation for emerging markets is available at the following link. The documents can be found in...