Proceedings

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

Junhao Liu, Haonan Yu, Zhenyu Yan, Xin Zhang

Download BibTeX Cite

Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence. Main Track. Pages 4572-4580.

https://doi.org/10.24963/ijcai.2026/509

Keywords

  • Natural Language Processing: Interpretability and analysis of models for NLP
  • Machine Learning: Explainable/Interpretable machine learning

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.

Junhao Liu, Haonan Yu, Zhenyu Yan, and Xin Zhang. 2026. Focus-LIME: Surgical Interpretation of Long-Context Large Language Models via Proxy-Based Neighborhood Selection. In Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26. IJCAI, 4572–4580. https://doi.org/10.24963/ijcai.2026/509
Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards