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
IRD Trading in Mainland China and Hong Kong
This report examines interest rate derivatives (IRD) trading activity in mainland China and Hong Kong in the first half of 2026. Onshore renminbi (RMB) IRD traded notional in mainland China rose to $3.4 trillion in the first half of 2026,...
ISDA In Review – October 2026
A compendium of links to new documents, research papers, press releases and comment letters published by ISDA in October 2026.
ISDA Recommendations on EMIR under MISP
On November 2, ISDA published its recommendations on the European Parliament compromise amendments to the European Market Infrastructure Regulation (EMIR) under the Market Integration and Supervision Package (MISP). The briefing covers five areas: transaction reporting (Article 9), non-financial counterparties (Article...
Response on UK MIFIR Reporting Guidelines
On November 6, ISDA responded to the Financial Conduct Authority’s (FCA) consultation CP26/34 ‘Preparing for the new transaction reporting regime’ on the upcoming changes to the UK Markets in Financial Instruments Regulation (MIFIR) transaction reporting regime, as set out in...