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

TL;DR

This paper introduces a procedural front-end pattern called bounded calibration with contestability for assisting LLM-enabled robots in multi-user social settings, aiming to manage pluralistic values and LLM variability effectively.

Contribution

It proposes a novel guardrail pattern that constrains assistance prioritization, enhances transparency, and provides contest pathways, addressing challenges of value pluralism and LLM unpredictability.

Findings

Pattern improves legibility of assistance modes

Enhances procedural legitimacy in multi-user interactions

Addresses risks of automation bias and usability issues

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.