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

Refreshing the FX Definitions

A lot has changed in the FX derivatives market since 1998, when the last set of standard definitions for FX transactions were published. Trading volumes have grown substantially, and average daily turnover has risen by six times. Market practices have...

ISDA & EMTA Publish New FX Definitions

ISDA and EMTA, Inc., the trade association for emerging markets, have jointly published a revised set of standard definitions for foreign exchange (FX) derivatives transactions, which update key market practices and consolidate various FX and FX-related product templates and provisions...

ISDA Position Paper on SFDR Review

On February 27, ISDA and the Association for Financial Markets in Europe (AFME) published a position paper on the European Commission’s (EC) proposed revisions to the Sustainable Finance Disclosure Regulation (SFDR 2.0). The paper welcomes the EC’s proposal as a...