Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

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

About

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.

Junhao Liu, Haonan Yu, Zhenyu Yan, Xin Zhang• 2026

Related benchmarks

TaskDatasetResultRank
Faithfulness EvaluationQasper yes/no question answering
AOPC@100.102
10
Showing 1 of 1 rows

Other info

Follow for update