Skin-in-the-Game: Decision Making via Multi-Stakeholder Alignment in LLMs
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914820424466432 |
|---|---|
| author | Sel, Bilgehan Shanmugasundaram, Priya Kachuee, Mohammad Zhou, Kun Jia, Ruoxi Jin, Ming |
| author_facet | Sel, Bilgehan Shanmugasundaram, Priya Kachuee, Mohammad Zhou, Kun Jia, Ruoxi Jin, Ming |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_12933 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Skin-in-the-Game: Decision Making via Multi-Stakeholder Alignment in LLMs Sel, Bilgehan Shanmugasundaram, Priya Kachuee, Mohammad Zhou, Kun Jia, Ruoxi Jin, Ming Computation and Language Artificial Intelligence Machine Learning 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. |
| title | Skin-in-the-Game: Decision Making via Multi-Stakeholder Alignment in LLMs |
| topic | Computation and Language Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2405.12933 |