Skin-in-the-Game：通过 LLMs 中的多利益相关者对齐进行决策
Skin-in-the-Game: Decision Making via Multi-Stakeholder Alignment in LLMs
AI总结：
本文提出 Skin-in-the-Game (SKIG) 框架，通过从多利益相关者视角探索决策后果、模拟问责机制、共情练习和风险评估，有效增强了大型语言模型在复杂场景下的道德推理与伦理决策能力。
摘要：
大型语言模型（LLMs）在摘要、算术推理和问答等任务中展现了卓越的能力。然而，它们在道德推理和伦理决策领域面临重大挑战，尤其是在涉及多个利益相关者的复杂场景中。本文提出了 Skin-in-the-Game (SKIG) 框架，旨在通过从多利益相关者视角探索决策后果来增强 LLMs 的道德推理能力。SKIG 机制的核心是模拟行为的问责机制，这与共情练习和风险评估一起，对其有效性至关重要。我们在各种道德推理基准上使用专有和开源 LLMs 验证了 SKIG 的性能，并通过广泛的消融分析研究了其关键组件。
英文摘要：
Large Language Models (LLMs) have shown remarkable capabilities in tasks such as summarization, arithmetic reasoning, and question answering. However, they encounter significant challenges in the domain of moral reasoning and ethical decision-making, especially in complex scenarios with multiple stakeholders. This paper introduces the Skin-in-the-Game (SKIG) framework, aimed at enhancing moral reasoning in LLMs by exploring decisions' consequences from multiple stakeholder perspectives. Central to SKIG's mechanism is simulating accountability for actions, which, alongside empathy exercises and risk assessment, is pivotal to its effectiveness. We validate SKIG's performance across various moral reasoning benchmarks with proprietary and opensource LLMs, and investigate its crucial components through extensive ablation analyses.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
