← back
arXivCharles Chang, Yuen Yuen Ang, Bolun SunFri, Oct 30, 2026, 6:48 PM PDT
score 15.0

Benchmark Tests Whether AI Can Track How Policies Change

Original: Dual-Axis Policy Entailment: A Benchmark for Policy-Change Reasoning

Source: arxiv.org ↗

Writing ELI5 summary…