← Back to all news
arXiv AI By Alaa Anani, Tobias Lorenz, Bernt Schiele, Mario Fritz, Jonas Fischer

Certified Circuits: Stability Guarantees for Mechanistic Circuits

Read the original on arXiv AI →

Certified Circuits introduces a framework that wraps any black‑box circuit discovery algorithm with randomized data subsampling to provide provable stability guarantees. By certifying that inclusion decisions over circuit components are invariant to bounded edit‑distance perturbations of the concept dataset, unstable components are abstained from, producing more compact and accurate mechanistic explanations. Across ResNet, ViT, and GPT‑2 on vision and language tasks, Certified Circuits achieves up to 56% higher accuracy and up to 80% fewer components, maintaining reliability where baseline methods degrade.

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 AI.

Related stories

arXiv Machine Learning
Aug 11

Can Graph Learning Learn Circuits?

arXiv:2608. 08536v1 Announce Type: new Abstract: Circuit localization is a mechanistic interpretability task whose goal is to identify a sparse subgraph of a transformer's computation graph sufficient to reproduce a particular behavior.

By Chester Tan, Moritz Lampert, Courtney Maynard, Ankit Ramakrishnan, Tina Eliassi-Rad, Ingo Scholtes
llmsbenchmarkssafety
More like this →
arXiv AI
Oct 26

Interpretable sparse fine-tuning with TopKLoRA enables faithful circuit discovery

The paper introduces TopKLoRA, an interpretable parameter‑efficient fine‑tuning method that activates only the top‑k adapter latents per token. Using this sparse LoRA, the authors fine‑tune large language models on a poisoned dataset, identify and ablate the minimal circuit responsible for a backdoor, and show that the resulting circuits are an order of magnitude smaller than dense LoRA baselines. They also demonstrate how to construct model organisms with localized circuits via gradient‑routing, supporting the development of interpretable‑by‑design architectures.

By Marek Masiak, Andrzej Szablewski, Nicola Cancedda, Constantin Venhoff
agentsfine-tuningbenchmarkssafety
More like this →
arXiv AI
Oct 5

Certified Mechanistic Edits: Behavioral Guarantees for Skill Removal and Preservation

Certified Mechanistic Edits: Behavioral Guarantees for Skill Removal and Preservation proposes a method to formally certify that disabling a specific circuit in a neural network removes a targeted skill while preserving another, for every input within a continuous region. The approach extends beyond testing by providing sound guarantees over continuous embedding-space regions, demonstrated on toy ReLU networks and a standard transformer. It also shows that no finite deterministic black-box test can guarantee removal, highlighting the necessity of formal verification.

By Md Sazid Uddin, Md. Khairul Alam Mazumder, M. F. Mridha
llmsragsafety
More like this →