Benchmarking Generative AI for CSA Clause Extraction and CDM Representation

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

ISDA Response on Common Carbon Data Model

On August 12, ISDA responded to a consultation from the Climate Data Steering Committee (CDSC) on a Common Carbon Credit Data Model. ISDA members believe the Group-of-20 carbon data model initiative is a positive step in addressing data gaps and...

Joint Response on RBA Consultation

On August 11, ISDA and FIA submitted a joint response to the Reserve Bank of Australia (RBA) on its consultation on guidance for Australia’s clearing and settlement facility resolution regime. The associations welcome publication of the draft guidance, which provides...

SwapsInfo H1 2025 and Q2 2025

Interest rate derivatives (IRD) trading activity increased in the first half of 2025, driven by continued interest rate volatility, evolving central bank policy expectations and persistent macroeconomic uncertainty. Trading in index credit derivatives also rose, as market participants responded to...