When Robots Say No: The Empathic Ethical Disobedience Benchmark

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kuzmenko, Dmytro, Shvai, Nadiya
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912979775127552
author Kuzmenko, Dmytro
Shvai, Nadiya
author_facet Kuzmenko, Dmytro
Shvai, Nadiya
contents Robots must balance compliance with safety and social expectations as blind obedience can cause harm, while over-refusal erodes trust. Existing safe reinforcement learning (RL) benchmarks emphasize physical hazards, while human-robot interaction trust studies are small-scale and hard to reproduce. We present the Empathic Ethical Disobedience (EED) Gym, a standardized testbed that jointly evaluates refusal safety and social acceptability. Agents weigh risk, affect, and trust when choosing to comply, refuse (with or without explanation), clarify, or propose safer alternatives. EED Gym provides different scenarios, multiple persona profiles, and metrics for safety, calibration, and refusals, with trust and blame models grounded in a vignette study. Using EED Gym, we find that action masking eliminates unsafe compliance, while explanatory refusals help sustain trust. Constructive styles are rated most trustworthy, empathic styles -- most empathic, and safe RL methods improve robustness but also make agents more prone to overly cautious behavior. We release code, configurations, and reference policies to enable reproducible evaluation and systematic human-robot interaction research on refusal and trust. At submission time, we include an anonymized reproducibility package with code and configs, and we commit to open-sourcing the full repository after the paper is accepted.
format Preprint
id arxiv_https___arxiv_org_abs_2512_18474
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle When Robots Say No: The Empathic Ethical Disobedience Benchmark
Kuzmenko, Dmytro
Shvai, Nadiya
Robotics
Human-Computer Interaction
Robots must balance compliance with safety and social expectations as blind obedience can cause harm, while over-refusal erodes trust. Existing safe reinforcement learning (RL) benchmarks emphasize physical hazards, while human-robot interaction trust studies are small-scale and hard to reproduce. We present the Empathic Ethical Disobedience (EED) Gym, a standardized testbed that jointly evaluates refusal safety and social acceptability. Agents weigh risk, affect, and trust when choosing to comply, refuse (with or without explanation), clarify, or propose safer alternatives. EED Gym provides different scenarios, multiple persona profiles, and metrics for safety, calibration, and refusals, with trust and blame models grounded in a vignette study. Using EED Gym, we find that action masking eliminates unsafe compliance, while explanatory refusals help sustain trust. Constructive styles are rated most trustworthy, empathic styles -- most empathic, and safe RL methods improve robustness but also make agents more prone to overly cautious behavior. We release code, configurations, and reference policies to enable reproducible evaluation and systematic human-robot interaction research on refusal and trust. At submission time, we include an anonymized reproducibility package with code and configs, and we commit to open-sourcing the full repository after the paper is accepted.
title When Robots Say No: The Empathic Ethical Disobedience Benchmark
topic Robotics
Human-Computer Interaction
url https://arxiv.org/abs/2512.18474