Measuring and mitigating overreliance is necessary for building human-compatible AI

Measuring and mitigating overreliance is necessary for building human-compatible AI

8 September 2025

Katherine M. Collins

Sunnie S. Y. Kim

K. J. Kevin Feng

Siddharth Swaroop

Ilia Sucholutsky

ArXiv (abs)PDF HTML

Papers citing "Measuring and mitigating overreliance is necessary for building human-compatible AI"

2 / 2 papers shown

Title
Critical or Compliant? The Double-Edged Sword of Reasoning in Chain-of-Thought Explanations Eunkyu Park Wesley Hanwen Deng Vasudha Varadarajan Mingxi Yan Gunhee Kim Maarten Sap Motahhare Eslami LRM 107 0 0 15 Nov 2025
Human-AI Collaboration with Misaligned Preferences Jiaxin Song Parnian Shahkar Kate Donahue Bhaskar Ray Chaudhury HAI 138 0 0 04 Nov 2025