Noam Kolt

Project

Research Direction: Legal Safety Evals

Developing a novel benchmark to empirically evaluate whether AI agents comply with the law when performing computer-use tasks. The benchmark will focus on particular application domains (e.g., commercial negotiation, website development) and specific areas of law (e.g., fraudulent misrepresentation, financial crime).

What I'm looking for in a Mentee

Track record of at least one first-authored research paper.

Bio

Noam Kolt is an Assistant Professor at the Hebrew University Faculty of Law and School of Computer Science and Engineering, where he leads the Governance of AI Lab (GOAL). The lab’s mission is to support safe and ethical AI through sociotechnical computer science and legal research, with a focus on governing autonomous AI agents, studying the role of law in technical alignment, and conducting legal safety and compliance evaluations. Prior work has been published in law reviews (Washington University Law Review, Notre Dame Law Review, Berkeley Technology Law Journal, Yale Law & Policy Review), computer science venues (NeurIPS, ICML, ACM FAccT, AIES), and general-interest journals (Patterns, Science).