Designing for Disagreement: Front-End Guardrails for Assistance Allocation in LLM-Enabled Robots
This addresses the challenge of designing fair and transparent assistance allocation systems for multi-user social robots, though it is incremental as it builds on existing governance and procedural approaches.
The paper tackles the problem of allocating scarce assistance in LLM-enabled robots amid pluralistic values and LLM variability by proposing a front-end guardrail pattern called bounded calibration with contestability, which constrains prioritization modes, ensures legibility, and provides contest pathways without requiring global rule changes.
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.