{"type":"ScholarlyArticle","title":"Focus-LIME: Surgical Interpretation of Long-Context Large Language Models via Proxy-Based Neighborhood Selection","authors":[{"name":"Junhao Liu","slug":"junhao-liu","given":"Junhao","family":"Liu","affiliation":""},{"name":"Haonan Yu","slug":"haonan-yu","given":"Haonan","family":"Yu","affiliation":""},{"name":"Zhenyu Yan","slug":"zhenyu-yan","given":"Zhenyu","family":"Yan","affiliation":""},{"name":"Xin Zhang","slug":"xin-zhang","given":"Xin","family":"Zhang","affiliation":""}],"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.","doi":"10.24963/ijcai.2026/509","url":"https://ijcai.org/proceedings/2026/509","pdf":"https://ijcai.org/proceedings/2026/0509.pdf","markdown":"https://ijcai.org/proceedings/2026/509.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/509","volume":{"slug":"2026","title":"Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2026","url":"https://ijcai.org/proceedings/2026/","year":2026,"location":"Bremen, Germany","dates":"15-21 August 2026","editors":"Diego Calvanese","isbn":"978-1-956792-09-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2026"},"section":"Machine Learning","track":"Main Track","number":509,"pages":{"first":4572,"last":4580},"keywords":["Natural Language Processing: Interpretability and analysis of models for NLP","Machine Learning: Explainable/Interpretable machine learning"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}