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
Future Path - IQ December 2025
At the start of ISDA’s 40th anniversary year, IQ convened the pioneers of the association to reflect on how a desperate need for standardization in the early days of the derivatives market brought dealers together to develop a dictionary of...
Steps to a Vibrant Derivatives Market: SOM Remarks
Steps to a Vibrant and Resilient Derivatives Market December 4, 2025 Remarks at the Mediterranean Partnership of Securities Regulators Scott O’Malia ISDA Chief Executive Officer Good afternoon and thank you to the Mediterranean Partnership of Securities Regulators (MPSR) for...
ISDA Response to BoE on Gilt Market Resilience
On November 28, ISDA responded to the Bank of England’s discussion paper on gilt market resilience. ISDA encourages the Bank of England, before introducing any significant policy changes that would affect the functioning of the gilt repo market, to consider...
Addressing Termination Troubles
When Enron announced a shock $618 million loss on October 16, 2001, it took a further 47 days until it filed for bankruptcy. For Bear Stearns, it took 266 days between its bailout of a structured credit fund run by...