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
CDS Market Dynamics: Record 2025
Global credit default swap (CDS) market activity reached a record $41.8 trillion in 2025, surpassing the previous peak of $38.7 trillion in 2022. Index CDS drove the increase, accounting for 93.3% of total activity and reaching a record $39.0 trillion....
ISDA Letter to CFTC on Public Interest Determinations for Event Contracts
On July 27, ISDA submitted a letter to the U.S. Commodity Futures Trading Commission (CFTC) on the CFTC’s proposed rulemaking on public interest determinations for event contracts published in the Federal Register on June 12, 2026. ISDA emphasized the importance...
ISDA Letter to BCBS on RMA Models
On July 24, ISDA wrote to the Basel Committee on Banking Supervision (BCBS) to request guidance on how the proposed Risk Mitigation Accounting (RMA) model under International Financial Reporting Standard (IFRS) 9/IFRS 7 should be treated for prudential regulatory capital...
US Treasury Repo Clearing Indicators June 2026
The ISDA-Actrix US Treasury Repo Market Clearing Indicators illustrate central clearing adoption in the US Treasury repo market. Sponsored cleared repo volumes are used as a proxy to monitor client participation in central clearing, a key objective of the Securities...