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
Response to EC Call for Evidence on Tax Omnibus
On March 30, ISDA, the International Securities Lending Association and the Association for Financial Markets in Europe responded to the European Commission’s (EC) call for evidence on the tax omnibus. The associations argue that inconsistent interpretation of “beneficial ownership” among...
Managing Risk for Australian Superannuation Funds
Assets managed by the Australian superannuation sector reached A$4.5 trillion in December 2025, equivalent to around 160% of Australia’s GDP. Given its size, the sector has rapidly expanded its global footprint, with the share of offshore investments growing as a...
Updated OTC Derivatives Compliance Calendar
ISDA has updated its global calendar of compliance deadlines and regulatory dates for the over-the-counter (OTC) derivatives space.
Next Steps on a Much Improved Basel III Endgame
Publication of the revised Basel III endgame proposal earlier this month marks an important step towards completion of the global capital reforms, giving banks much-needed clarity on the likely calibration of the rules in the US. The new proposal is...