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

ISDA Omnibus Canadian Representation Letter

On September 2, ISDA published the Omnibus Canadian Representation Letter, which combines previously published representation letters drafted to assist firms in compliance with Canadian trade reporting, business conduct, regulatory margin and clearing classification rules. The Omnibus Canadian Letter is designed...

Joint Response on Cross-margining

On August 31, ISDA and FIA submitted a letter to the US Commodity Futures and Trading Commission (CFTC) and the Securities and Exchange Commission (SEC) on the agencies’ joint request for comment on the implementation of portfolio margining and cross-margining...