Designing for Disagreement: Front-End Guardrails for Assistance Allocation in LLM-Enabled Robots

arXiv cs.AI / 3/18/2026

📰 NewsIdeas & Deep AnalysisModels & Research

共有:

Key Points

The authors propose bounded calibration with contestability as a front-end pattern for allocating scarce assistance among multiple users in LLM-enabled robots.
The pattern constrains prioritization to a governance-approved menu of admissible modes and keeps the active mode legible at the point of deferral.
It provides an outcome-specific contest pathway without renegotiating the global rule to accommodate pluralism and LLM variability.
The paper outlines an evaluation agenda focused on legibility, procedural legitimacy, and actionability, including risks of automation bias and uneven usability of contest channels, illustrated by a public-concourse robot vignette.

Abstract

LLM-enabled robots prioritizing scarce assistance in social settings face pluralistic values and LLM behavioral variability: reasonable people can disagree about who is helped first, while LLM-mediated interaction policies vary across prompts, contexts, and groups in ways that are difficult to anticipate or verify at contact point. Yet user-facing guardrails for real-time, multi-user assistance allocation remain under-specified. We propose bounded calibration with contestability, a procedural front-end pattern that (i) constrains prioritization to a governance-approved menu of admissible modes, (ii) keeps the active mode legible in interaction-relevant terms at the point of deferral, and (iii) provides an outcome-specific contest pathway without renegotiating the global rule. Treating pluralism and LLM uncertainty as standing conditions, the pattern avoids both silent defaults that hide implicit value skews and wide-open user-configurable "value settings" that shift burden under time pressure. We illustrate the pattern with a public-concourse robot vignette and outline an evaluation agenda centered on legibility, procedural legitimacy, and actionability, including risks of automation bias and uneven usability of contest channels.