Revitalizing Black-Box Interpretability: Actionable Interpretability for LLMs via Proxy Models
Year: 2026
Type: conference-paper
Abstract: Post-hoc explanations provide transparency and are essential for guiding model optimization, such as prompt engineering and data sanitation.However, applying model-agnostic techniques to Large Language Models (LLMs) is hindered by prohibitive computational costs, rendering these tools dormant for real-world applications.To revitalize model-agnostic interpretability, we propose a budget-friendly proxy framework that leverages efficient models to approximate the decision boundaries of expensive LLMs.We introduce a screen-and-apply mechanism to statistically verify local alignment before deployment.Our empirical evaluation confirms that proxy explanations achieve over 90% fidelity with only 9.5% of the oracle's cost.Building on this foundation, we demonstrate the actionable utility of our framework in prompt compression and poisoned example removal.Results show that reliable proxy explanations effectively guide optimization, transforming interpretability from a passive observation tool into a scalable primitive for LLM development.Additionally, we open-source code and datasets to facilitate future research 1 .
Authors: Junhao Liu, Haonan Yu, Zhenyu Yan, Xin Zhang
Institution: Peking University
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
Award: G5212030523
OpenAlex ID: W4417301055