RobotValues: Evaluating Household Robots When Human Values Conflict

Hugging Face Daily Papers Papers

Summary

Introduces RobotValues, a benchmark of 10K value-conflict scenarios for evaluating household robot planners, showing that vision-language models exhibit default value preferences and fail to override them 80% of the time when instructed to prioritize conflicting values.

While household robots are often evaluated based on task completion, everyday domestic environments involve value-conflicting situations in which robots are expected to choose actions that prioritize other values than task success, such as human autonomy, efficiency, or social appropriateness. Yet, there are no benchmarks for evaluating robots' value preferences in such scenarios. We introduce RobotValues, a benchmark to evaluate household robot planners in 10K value-conflict scenarios. Each instance consists of a realistic household image with multiple plausible robot actions that prioritize different human values. We construct RobotValues through LLM-assisted scenario generation, stakeholder-grounded value extraction, image generation and automatic quality control. Using RobotValues we evaluate VLMs used in robotics and find that models exhibit default value preferences, including safety and accommodation, while underselecting privacy-prioritizing actions. When the models are instructed to prioritize specific values that conflict with their own preferences, they often fail to override their default actions, choosing incorrect actions for 80% of the time. These findings suggest that household robot evaluation should measure not only task completion or safety compliance, but also whether robots can choose among plausible actions when human values conflict.
Original Article
View Cached Full Text

Cached at: 06/05/26, 06:06 AM

Paper page - RobotValues: Evaluating Household Robots When Human Values Conflict

Source: https://huggingface.co/papers/2606.03312

Abstract

RobotValues benchmark evaluates household robot planners in value-conflict scenarios, revealing that vision-language models exhibit default value preferences and struggle to override them when instructed to prioritize conflicting values.

Whilehousehold robotsare often evaluated based on task completion, everyday domestic environments involve value-conflicting situations in which robots are expected to choose actions that prioritize other values than task success, such as human autonomy, efficiency, or social appropriateness. Yet, there are no benchmarks for evaluating robots’ value preferences in such scenarios. We introduceRobotValues, a benchmark to evaluate household robot planners in 10Kvalue-conflict scenarios. Each instance consists of a realistic household image with multiple plausible robot actions that prioritize different human values. We constructRobotValuesthroughLLM-assisted scenario generation,stakeholder-grounded value extraction,image generationandautomatic quality control. UsingRobotValueswe evaluate VLMs used in robotics and find that models exhibit default value preferences, including safety and accommodation, while underselecting privacy-prioritizing actions. When the models are instructed to prioritize specific values that conflict with their own preferences, they often fail to override their default actions, choosing incorrect actions for 80% of the time. These findings suggest that household robot evaluation should measure not only task completion or safety compliance, but also whether robots can choose among plausible actions when human values conflict.

View arXiv pageView PDFAdd to collection

Get this paper in your agent:

hf papers read 2606\.03312

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2606.03312 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2606.03312 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2606.03312 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies

Hugging Face Daily Papers

RoboLab is a high-fidelity simulation benchmarking framework for evaluating task-generalist robotic policies, introducing the RoboLab-120 benchmark with 120 tasks across visual, procedural, and relational competency axes. It enables scalable, realistic task generation and systematic analysis of policy behavior under controlled perturbations to assess true generalization capabilities.

What Do People Actually Want From AI? Mapping Preference Plurality

arXiv cs.CL

This paper analyzes 1,500 open-ended responses from 75 countries to reveal that people have diverse and often conflicting preferences for AI, with truthfulness being the only widely demanded value (49%), yet defined in incompatible ways. It argues that current RLHF methods flatten these pluralistic preferences into universal reward models, perpetuating epistemic violence.

Robots Need More than VLA and World Models

Hugging Face Daily Papers

This position paper argues that advancing robot intelligence requires integrating unstructured behavioral data through specialized interfaces for labeling, embodiment mapping, world modeling, and reward inference, rather than relying solely on scaling Vision-Language-Action (VLA) models and world models.