skin-in-the-game.github.io Open in urlscan Pro
2606:50c0:8003::153  Public Scan

Form analysis
0 forms found in the DOM

Text Content

SKIN-IN-THE-GAME: DECISION MAKING VIA MULTI-STAKEHOLDER ALIGNMENT IN LLMS

Bilgehan Sel1, Priya Shanmugasundaram1, Mohammad Kachuee2, Kun Zhou2, Ruoxi
Jia1, Ming Jin1
1Virginia Tech, 2Amazon
ACL 2024
Paper Code arXiv


ABSTRACT

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.


SKIN IN THE GAME WORKFLOW. EACH BOX SIGNIFIES A DISTINCT THOUGHT, FUNCTIONING AS
A UNIFIED STRING OF WORDS THAT FORMS AN INCREMENTAL PATHWAY TO REASONING.


BIBTEX

@article{sel2024skin,
  title={Skin-in-the-Game: Decision Making via Multi-Stakeholder Alignment in LLMs},
  author={Sel, Bilgehan and Shanmugasundaram, Priya and Kachuee, Mohammad and Zhou, Kun and Jia, Ruoxi and Jin, Ming},
  journal={arXiv preprint arXiv:2405.12933},
  year={2024}
}