为大模型决策系统设计可解释性方法，解决随机推理下的归因难题。
llmSHAP: A Principled Approach to LLM Explainability
- 基于博弈论的谢尔普利值，适配大模型的随机推理特性。
- 揭示不同实现方式下可解释性原则的满足条件与失效场景。
- 平衡解释速度、准确性与理论一致性，适合可信AI研究者。
特征归因方法通过量化单个或多个特征对模型输出的贡献，提升机器学习推理的可解释性。其中，基于合作博弈论中谢尔普利值的方法尤为流行，该方法在确定性推理下能保证多项理想性质。本文将谢尔普利值应用于基于大语言模型（LLM）的决策支持系统，而此类系统的推理本质上是随机的（非确定性）。我们分析了在不同实现变体下，能否保证谢尔普利值性质的成立，并研究了大模型随机性对这些性质的破坏机制。同时，我们揭示了可解释性推理速度、与精确谢尔普利值的一致性以及理论原则满足度之间的权衡关系。
原文摘要 · Abstract (English)
Feature attribution methods help make machine learning-based inference explainable by determining how much one or several features have contributed to a model's output. A particularly popular attribution method is based on the Shapley value from cooperative game theory, a measure that guarantees the satisfaction of several desirable principles, assuming deterministic inference. We apply the Shapley value to feature attribution in large language model (LLM)-based decision support systems, where inference is, by design, stochastic (non-deterministic). We then demonstrate when we can and cannot guarantee Shapley value principle satisfaction across different implementation variants applied to LLM-based decision support, and analyze how the stochastic nature of LLMs affects these guarantees. We also highlight trade-offs between explainable inference speed, agreement with exact Shapley value attributions, and principle attainment.
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。