Focus-LIME: 通过基于代理的邻域选择实现长上下文大语言模型的手术解释
Focus-LIME: Surgical Interpretation of Long-Context Large Language Models via Proxy-Based Neighborhood Selection
AI总结：
Focus-LIME通过基于代理的邻域选择方法，实现长上下文大语言模型的手术级解释，解决了高维特征空间下的归因稀释问题。
摘要：
随着大语言模型（LLMs）扩展以处理大规模上下文窗口，实现手术级别的特征解释对于高风险任务如法律审计和代码调试至关重要。然而，现有的局部模型无关解释方法在这些场景中面临关键困境：基于特征的方法由于高维特征空间导致归因稀释，从而无法提供忠实的解释。在本文中，我们提出了Focus-LIME，一种从粗到细的框架，旨在恢复手术解释的可操作性。Focus-LIME利用代理模型来精选扰动邻域，使目标模型能够在优化的上下文中执行细粒度归因。在长上下文基准上的实证评估表明，我们的方法使手术解释成为可能，并为用户提供忠实的解释。
英文摘要：
As Large Language Models (LLMs) scale to handle massive context windows, achieving surgical feature-level interpretation is essential for high-stakes tasks like legal auditing and code debugging. However, existing local model-agnostic explanation methods face a critical dilemma in these scenarios: feature-based methods suffer from attribution dilution due to high feature dimensionality, thus failing to provide faithful explanations. In this paper, we propose Focus-LIME, a coarse-to-fine framework designed to restore the tractability of surgical interpretation. Focus-LIME utilizes a proxy model to curate the perturbation neighborhood, allowing the target model to perform fine-grained attribution exclusively within the optimized context. Empirical evaluations on long-context benchmarks demonstrate that our method makes surgical explanations practicable and provides faithful explanations to users.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
