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
Response to ESMA Guarantees
On April 30, ISDA responded to the European Securities and Markets Authority (ESMA) consultation paper on guarantees as central counterparty (CCP) collateral and certain aspects of CCP investment policy. ISDA broadly supports ESMA’s proposed draft regulatory technical standards (RTS) to...
ISDA AGM Studio: Jenny Cosco and Jason Granet
Jenny Cosco, global head of government relations and regulatory strategy at LSEG, and Jason Granet, chief investment officer at BNY, speak with Tara Kruse, ISDA’s global head of derivative products and infrastructure, about how firms can manage liquidity pressures during...
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.
Capital Models Benchmarking: A Framework for Counterparty Credit Risk Internal Models
When firms implement capital models in line with supervisory standards, a range of interpretative and implementation choices inevitably arise. These choices reflect differences in modeling approaches, data availability, system architecture and risk management practices, and can lead to variation in...