---
title: "Focus-LIME: Surgical Interpretation of Long-Context Large Language Models via Proxy-Based Neighborhood Selection"
authors:
  - "Junhao Liu"
  - "Haonan Yu"
  - "Zhenyu Yan"
  - "Xin Zhang"
doi: "10.24963/ijcai.2026/509"
url: "https://ijcai.org/proceedings/2026/509"
pdf: "https://ijcai.org/proceedings/2026/0509.pdf"
venue: "Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence"
year: 2026
pages: "4572-4580"
track: "Main Track"
keywords:
  - "Natural Language Processing: Interpretability and analysis of models for NLP"
  - "Machine Learning: Explainable/Interpretable machine learning"
---

# Focus-LIME: Surgical Interpretation of Long-Context Large Language Models via Proxy-Based Neighborhood Selection

Junhao Liu, Haonan Yu, Zhenyu Yan, Xin Zhang

*Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence*, pages 4572-4580. DOI: [10.24963/ijcai.2026/509](https://doi.org/10.24963/ijcai.2026/509)

## Abstract

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, which prevents them from providing 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 practical and provides faithful explanations to users.