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

Joint Response to EBA Consultation

On August 12, ISDA and the Association for Financial Markets in Europe (AFME) responded to the European Banking Authority’s discussion paper on certain taxonomy key performance indicators (KPIs) and other aspects of the Disclosures Delegated Act  under Article 8 of...

Response to JSCC on Clearing Fund Consolidation

On August 12, ISDA responded to the Japan Securities Clearing Corporation’s (JSCC) consultation on its proposal to consolidate clearing fund consumption, calculation and deposit segmentation across six clearing qualifications under the Financial Instruments and Exchange Act. ISDA members broadly support...

Response on CSDD Guidelines

On August 6, ISDA responded to the European Commission’s (EC) consultation on due diligence guidelines under the Corporate Sustainability Due Diligence Directive (CSDDD). While ISDA acknowledges that model contractual clauses can be a helpful resource for in-scope companies, there are...