为大模型机器人设计可争议的辅助分配机制，平衡多元价值与模型不确定性。
Designing for Disagreement: Front-End Guardrails for Assistance Allocation in LLM-Enabled Robots
- 限定优先级为预审通过的选项菜单，避免随意配置
- 实时展示当前分配模式，确保交互透明可理解
- 提供针对结果的申诉通道，无需重订全局规则
配备大模型的机器人在社交场景中分配稀缺协助时，面临多元价值观和大模型行为波动：合理的人可能对谁应优先帮助存在分歧，而大模型的交互策略在不同提示、上下文和群体间变化难以预测或验证。然而，面向用户的实时多用户协助分配防护机制仍不明确。本文提出‘有限校准+可争议性’的前端模式，包含三要素：(i) 将优先级限制在治理批准的可接受模式菜单内；(ii) 在需决策点以交互相关术语保持当前模式清晰可见；(iii) 提供不重新协商全局规则的结果特定申诉路径。将多元主义与大模型不确定性视为常态，该模式既避免隐藏隐含价值偏移的默认设置，也规避在时间压力下将责任转移给用户的全开放配置。通过公共走廊机器人案例说明该模式，并提出以可读性、程序正当性和可操作性为中心的评估议程，涵盖自动化偏见及申诉渠道使用不均等风险。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。