The Information Machine

Stanford researchers found that law professors preferred AI answers over peer professor answers 75% of the time when jud…

Rohan Paul Twitter · Rohan Paul (@rohanpaul_ai) · 2026-06-02

A Stanford study finds law professors preferred AI-generated contract-law answers over those from peer professors 75% of the time in a blind evaluation, challenging assumptions about AI limitations in argument-based legal reasoning.

Open original ↗

Appears in

Extraction

Topics: legal-aillm-evaluationlaw-educationai-vs-human-comparison

Claims

  • Law professors preferred AI answers over peer professor answers 75% of the time in a Stanford contract-law blind evaluation.
  • The study specifically tested LLMs in a domain requiring defensible arguments rather than factual recall.
  • AI may perform comparably to or better than human experts in legal education contexts.

Key quotes

Stanford researchers found that law professors preferred AI answers over peer professor answers 75% of the time when judging contract-law help for students.
The study tested whether LLMs can handle a field where the answer is often not a fact, but a defensible argument built...