BlackboxNLP-2025 MIB Shared Task: Improving Circuit Faithfulness via Better Edge Selection

📝 Original Info

• Title: BlackboxNLP-2025 MIB Shared Task: Improving Circuit Faithfulness via Better Edge Selection
• ArXiv ID: 2510.25786
• Date: 2025-10-28
• Authors: 저자 정보가 논문 본문에 명시되지 않아 제공할 수 없습니다.

📝 Abstract

One of the main challenges in mechanistic interpretability is circuit discovery, determining which parts of a model perform a given task. We build on the Mechanistic Interpretability Benchmark (MIB) and propose three key improvements to circuit discovery. First, we use bootstrapping to identify edges with consistent attribution scores. Second, we introduce a simple ratio-based selection strategy to prioritize strong positive-scoring edges, balancing performance and faithfulness. Third, we replace the standard greedy selection with an integer linear programming formulation. Our methods yield more faithful circuits and outperform prior approaches across multiple MIB tasks and models. Our code is available at: https://github.com/technion-cs-nlp/MIB-Shared-Task.

💡 Deep Analysis

📄 Full Content

Reference