Skin-in-the-Game: Decision Making via Multi-Stakeholder Alignment in LLMs
This addresses the problem of improving ethical decision-making in LLMs for applications involving multiple stakeholders, representing an incremental advancement in moral reasoning frameworks.
The paper tackles the challenge of moral reasoning and ethical decision-making in LLMs for complex scenarios with multiple stakeholders by introducing the Skin-in-the-Game (SKIG) framework, which simulates accountability and incorporates empathy and risk assessment, and validates its performance across benchmarks with proprietary and open-source LLMs.
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.