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
FRTB Impact on Correlation Trading
The capitalization of the correlation trading portfolio (CTP) under the Fundamental Review of the Trading Book will have an adverse economic impact for users of these instruments. In particular, there is a lack of clarity and consistency in the application...
ISDA In Review – September 2025
A compendium of links to new documents, research papers, press releases and comment letters published by ISDA in September 2025.
A Path to Greater CFTC-SEC Alignment
Earlier this week, the Commodity Futures Trading Commission (CFTC) and the Securities and Exchange Commission (SEC) held a roundtable on regulatory harmonization – an initiative we wholeheartedly support. The US regulatory framework has evolved over time to facilitate financial markets...
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.