arXiv Machine Learning June 2, 2026 By Joakim Edin, Casper L. Christensen, R\'obert Csord\'as, Tuukka Ruotsalo, Zhengxuan Wu, Maria Maistro, Jing Huang, Lars Maal{\o}e

Correcting Gradient-Based Circuit Localization via Interaction-Aware Backpropagation

Read the original on arXiv Machine Learning →

arXiv:2505. 17630v4 Announce Type: replace-cross Abstract: Circuit localization methods aim to identify the subset of model components responsible for specific behaviors in large language models, enabling detailed mechanistic analysis.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv AI

Sep 2

S^3martCirc: Self-supervised Smart Circuit Discovery

S^3martCirc is a self‑supervised framework that jointly discovers and interprets neural circuits in large language models, rather than treating circuit discovery and functional interpretation as separate stages. It abstracts node behavior into two general computational roles that generalize across tasks and introduces a quantitative metric for assigning these roles, enabling simultaneous identification of importance and function. Experiments demonstrate that S^3martCirc outperforms existing methods in circuit discovery.

By Wendy Zheng, Yinhan He, Liang Wu, Jundong Li

llms nlp safety

arXiv Machine Learning

Aug 7

CircuitSteer: Geometrically Aligned Multi-Layer Steering via Sparse Autoencoder Circuits

arXiv:2608. 05732v1 Announce Type: new Abstract: Controlling the behavior of large language models (LLMs) remains a critical challenge for AI alignment.

By Mehrshad Saadatinia, Parsa Razmara, Ardalan Aryashad, Ali Abbasi, Seyedarmin Azizi

llms safety

arXiv AI

Jun 16

Scalable Circuit Learning for Interpreting Large Language Models

arXiv:2606. 16939v1 Announce Type: cross Abstract: A prominent research direction in mechanistic interpretability is learning sparse circuits over LLM components to reveal how they jointly produce model behavior.

By Naiyu Yin, Dennis Wei, Tian Gao, Amit Dhurandhar, Karthikeyan Natesan Ramamurthy, Yue Yu

llms benchmarks safety

arXiv AI

Aug 26

Beyond Static Interpretability: Anticipating Post-SFT Mechanisms from Pre-SFT Parameters for Better Tuning

arXiv:2608.24482v1 Announce Type: cross Abstract: Mechanistic Localization bridges mechanistic interpretability and post-training optimization by isolating critical parameters via interpretative appr...

By Hang Chen, Jiaying Zhu, Wenya Wang

fine-tuning safety

arXiv Machine Learning

4d ago

RESCUE: Repairing Language Model Errors to Sparse Circuits via Reinforcement Learning

arXiv:2609.36813v1 Announce Type: new Abstract: Large language models (LLMs) exhibit strong general capabilities that mechanistic interpretability has attributed to sparse computational circuits. How...

By Chuanpu Liu, Miao Yu, Yikai Cai, Yuanhe Zhang, Zhenhong Zhou, Li Sun, Zuming Jiang, Yufei Guo

llms reinforcement-learning fine-tuning efficiency safety

arXiv AI

Sep 21

Decoupling Internal Representational Changes and Causal Importance in Fine-Tuned Large Language Models

Fine‑tuning reshapes internal representations of large language models, affecting attention patterns and layer‑wise activations. The study shows that components identified by EAP as important for task performance cluster in specific layers, yet these layers do not align with those undergoing the largest representational changes. Additionally, overlapping EAP components across different tasks do not guarantee cross‑task transfer and can even degrade performance when tasks differ in nature.

By Lingfang Li, Procheta Sen, Shubham Das, Danushka Bollegala

llms fine-tuning

One email a morning, machine-written

Related stories

S^3martCirc: Self-supervised Smart Circuit Discovery

CircuitSteer: Geometrically Aligned Multi-Layer Steering via Sparse Autoencoder Circuits

Scalable Circuit Learning for Interpreting Large Language Models

Beyond Static Interpretability: Anticipating Post-SFT Mechanisms from Pre-SFT Parameters for Better Tuning

RESCUE: Repairing Language Model Errors to Sparse Circuits via Reinforcement Learning

Decoupling Internal Representational Changes and Causal Importance in Fine-Tuned Large Language Models