Employers and landlords often draft contracts with ambiguous or unreasonable clauses, leaving employees and tenants vulnerable to unfair terms. In response, researchers at New York University have developed an innovative tool designed to identify and flag these problematic passages, offering a new layer of protection for second parties.
For instance, a common lease phrase like “Tenant must provide written notice of intent to vacate at a reasonable time” is ambiguous due to the undefined nature of “reasonable.” Similarly, clauses such as “Employee agrees not to work for any business in the United States for two years following termination” are unenforceable in many states that prohibit broad non-compete agreements.
Introducing ContractNerd: A New Era in Contract Analysis
To address these issues, the NYU team has created ContractNerd, a tool that uses large language models (LLMs) to analyze contracts and categorize clauses into four types: missing clauses, unenforceable clauses, legally sound clauses, and legal but risky clauses. The tool further identifies the latter as “high risk,” “medium risk,” or “low risk.”
According to Dennis Shasha, Silver Professor of Computer Science at NYU’s Courant Institute of Mathematical Sciences and senior author of the research published in MDPI Electronics, “Many of us have to read and decide whether or not to sign contracts, but few of us have the legal training to understand them properly. ContractNerd is an AI system that analyzes contracts for clauses that are missing, are extremely biased, are often illegal, or are ambiguous—and will suggest improvements to them.”
How ContractNerd Works
ContractNerd currently analyzes leases and employment contracts in New York City and Chicago, utilizing sources such as Thomson Reuters Westlaw, Justia, and Agile Legal, alongside state regulations, to spot contractual risks. The tool’s effectiveness was evaluated through several methods, showing superior performance compared to existing AI systems.
In one comparison, ContractNerd achieved the highest scores in predicting unenforceable clauses in legal cases. In another, an independent panel of laypersons evaluated the outputs of ContractNerd and a competitor, goHeather, based on relevance, accuracy, and completeness. ContractNerd received higher ratings overall.
Expert Evaluations and Insights
NYU School of Law Professor Clayton Gillette, an expert in contracts law, provided qualitative assessments of both systems. He found ContractNerd to be more thorough, though noted that goHeather’s analysis was easier to comprehend.
“Contracts are of course about law, but they should also be fair to both parties,” says Shasha. “We see ContractNerd as an aid that can help guide users in determining if a contract is both legal and fair, potentially heading off both risky agreements and future legal disputes.”
The Implications and Future of ContractNerd
The development of ContractNerd represents a significant advancement in contract analysis, offering a practical solution for navigating complex legal documents. By identifying risky clauses, the tool aims to prevent unfair agreements and reduce potential legal disputes.
The creators of ContractNerd plan to expand its geographic reach, potentially broadening its impact across different legal jurisdictions. As the tool evolves, it may become an essential resource for both contract drafters and signers, ensuring greater fairness and clarity in contractual agreements.
The paper’s other authors, Musonda Sinkala and Yuge Duan, were NYU graduate students at the time the prototype was built, along with Haowen Yuan, an NYU undergraduate. Their collective efforts have laid the groundwork for a tool that could reshape the landscape of contract law.
