用博弈论方法公平分配AI生成内容的创作功劳。
In-Context Credit Assignment via the Core
- 基于合作博弈的最小核心解法，确保各贡献者不被严重低估。
- 新算法减少数个数量级的LLM调用次数，效率显著提升。
- 适合需要公平激励创作者的AI内容生成场景。
我们提出了一种激励对齐的上下文信用分配机制：即在生成内容（如代码、新闻、短视频）时，如何公平分配因使用了多个创作者知识产权而产生的信用。该方法基于合作博弈论中的最小核心解概念，通过确保任何创作者子集都不会显著低于其独立创造的价值，实现最稳定的收益分配。我们开发了用于近似最小核心的新算法，利用创新的约束种子和约束分离技术。在网页检索信用分配任务中，我们的方法相比其他方法可减少数个数量级的LLM调用次数，显著提升了效率。
原文摘要 · Abstract (English)
We propose incentive-aligned mechanisms for in-context credit assignment: the task of assigning credit for AI-generated content (e.g. code, news articles, short-form videos) among creators whose intellectual property appears in the context window. Our approach is based on the least core solution concept from cooperative game theory, which distributes value in a way that is as stable as possible by ensuring that no subset of creators is significantly under-compensated relative to the value they could generate on their own. We develop algorithms for approximating the least core, which leverage novel routines for constraint seeding and constraint separation. On a web retrieval credit assignment task, we find that our approaches are capable of approximating the least core using orders of magnitude fewer LLM calls compared to alternative methods.
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。