用高效算法实现生成式搜索中内容贡献的公平分配
MaxShapley: Towards Incentive-compatible Generative Search with Fair Context Attribution
- 基于可分解最大和效用函数，实现多项式时间计算
- 在三个多跳问答数据集上达到与精确谢波德值相当的准确率
- 资源消耗降低最多9倍，适合大规模生成式搜索场景
基于大语言模型的生成式搜索引擎正在取代传统搜索，深刻改变信息提供者的收益模式。为维持这一生态，需要公平的机制来根据内容对生成答案的贡献进行归因与补偿。本文提出MaxShapley，一种针对检索外部来源后生成的管道的高效公平归因算法。MaxShapley是著名谢波德值的特例，利用可分解的最大和效用函数，实现了在文档数量上的多项式时间计算，相比谢波德值的指数成本大幅降低。我们在三个多跳问答数据集（HotPotQA、MuSiQUE、MS MARCO）上评估了该方法，结果表明其归因质量与精确谢波德值相当，同时显著减少资源消耗——例如，在相同归因精度下，相比现有最先进方法最多可降低9倍的资源开销。代码与重新校准的数据集已开源，教育演示可通过https://fair-search.com访问。
原文摘要 · Abstract (English)
Generative search engines based on large language models (LLMs) are replacing traditional search, fundamentally changing how information providers are compensated. To sustain this ecosystem, we need fair mechanisms to attribute and compensate content providers based on their contributions to generated answers. We introduce MaxShapley, an efficient algorithm for fair credit attribution in generative search pipelines that retrieve external sources before generation. MaxShapley is a special case of the celebrated Shapley value; it leverages a de-composable max-sum utility function to compute attributions with polynomial-time computation in the number of documents, as opposed to the exponential cost of Shapley values. We evaluate MaxShapley on three multi-hop QA datasets (HotPotQA, MuSiQUE, MS MARCO); MaxShapley achieves comparable attribution quality to exact Shapley computation, while consuming a fraction of its tokens--for instance, it gives up to a 9x reduction in resource consumption over prior state-of-the-art methods at the same attribution accuracy. We release open-source code and re-calibrated datasets. An educational demo is available at https://fair-search.com.
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。