paper-with-me

홈 › Papers

IBCircuit: Towards Holistic Circuit Discovery with Information Bottleneck

2026-02-26 · Tian Bian, Yifan Niu, Chaohao Yuan, Chengzhi Piao, Bingzhe Wu, Long-Kai Huang, Yu Rong, Tingyang Xu, Hong Cheng, Jia Li arxiv

Circuit discovery has recently attracted attention as a potential research direction to explain the non-trivial behaviors of language models. It aims to find the computational subgraphs, also known as circuits, within the model that are responsible for solving specific tasks. However, most existing studies overlook the holistic nature of these circuits and require designing specific corrupted activations for different tasks, which is inaccurate and inefficient. In this work, we propose an end-to-end approach based on the principle of Information Bottleneck, called IBCircuit, to identify informative circuits holistically. IBCircuit is an optimization framework for holistic circuit discovery and can be applied to any given task without tediously corrupted activation design. In both the Indirect Object Identification (IOI) and Greater-Than tasks, IBCircuit identifies more faithful and minimal circuits in terms of critical node components and edge components compared to recent related work.

📄 PDF Abstract BibTeX arXiv:2602.22581

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Investigating the Indirect Object Identification circuit in Mamba

2024-07-19 · Danielle Ensign, Adrià Garriga-Alonso

How well will current interpretability techniques generalize to future models? A relevant case study is Mamba, a recent recurrent architecture with scaling comparable to Transformers. We adapt pre-Mamba techniques to Mam…

MambaObjectPosition

Arbitrary Precision Printed Ternary Neural Networks with Holistic Evolutionary Approximation

2025-08-27 · Vojtech Mrazek, Konstantinos Balaskas, Paula Carolina Lozano Duarte, Zdenek Vasicek 외 arxiv

Printed electronics offer a promising alternative for applications beyond silicon-based systems, requiring properties like flexibility, stretchability, conformality, and ultra-low fabrication costs. Despite the large fea…

Attribution-guided Pruning for Compression, Circuit Discovery, and Targeted Correction in LLMs

2025-06-16 · Sayed Mohammad Vakilzadeh Hatefi, Maximilian Dreyer, Reduan Achtibat, Patrick Kahardipraja 외

Large Language Models (LLMs) are central to many contemporary AI applications, yet their extensive parameter counts pose significant challenges for deployment in memory- and compute-constrained environments. Recent works…

Model Compression

When In-memory Computing Meets Spiking Neural Networks -- A Perspective on Device-Circuit-System-and-Algorithm Co-design

2024-08-22 · Abhishek Moitra, Abhiroop Bhattacharjee, Yuhang Li, Youngeun Kim 외

This review explores the intersection of bio-plausible artificial intelligence in the form of Spiking Neural Networks (SNNs) with the analog In-Memory Computing (IMC) domain, highlighting their collective potential for l…

Edge-computing

Graph-Based Bayesian Optimization for Quantum Circuit Architecture Search with Uncertainty Calibrated Surrogates

2025-12-10 · Prashant Kumar Choudhary, Nouhaila Innan, Muhammad Shafique, Rajeev Singh arxiv

Quantum circuit design is a key bottleneck for practical quantum machine learning on complex, real-world data. We present an automated framework that discovers and refines variational quantum circuits (VQCs) using graph-…

Quantum Machine LearningGraph Neural Network