Certified Circuits: Stability Guarantees for Mechanistic Circuits

2026-02-26 · Alaa Anani, Tobias Lorenz, Bernt Schiele, Mario Fritz, Jonas Fischer arxiv

Understanding how neural networks arrive at their predictions is essential for debugging, auditing, and deployment. Mechanistic interpretability pursues this goal by identifying circuits--minimal subnetworks responsible for specific behaviors. However, existing circuit discovery methods are brittle: circuits depend strongly on the chosen concept dataset and often fail to transfer out-of-distribution, raising doubts whether they capture the concept or merely dataset-specific artifacts. We introduce Certified Circuits, which provide provable stability guarantees for circuit discovery. Our framework wraps any black-box discovery algorithm with randomized data subsampling to certify that inclusion decisions over circuit components--neurons or edges of the model graph, depending on the base algorithm--are invariant to bounded edit-distance perturbations of the concept dataset. Unstable components are abstained from, yielding circuits that are more compact and more accurate. We validate across three architectures (ResNet, ViT, GPT-2) on vision (ImageNet and four OOD datasets) and language (IOI, IOI-Hard, Greater-Than) tasks. Certified circuits achieve up to 56% higher accuracy and up to 80% fewer components, and remain reliable where baselines degrade. Certified Circuits puts circuit discovery on formal ground by producing mechanistic explanations that are provably stable and better aligned with the target concept. Code: https://github.com/AlaaAnani/certified-circuits.

📄 PDF Abstract BibTeX arXiv:2602.22968

Code (0)

등록된 구현이 없습니다.

Formal Mechanistic Interpretability: Automated Circuit Discovery with Provable Guarantees

2026-02-18 · Itamar Hadad, Guy Katz, Shahaf Bassan arxiv

*Automated circuit discovery* is a central tool in mechanistic interpretability for identifying the internal components of neural networks responsible for specific behaviors. While prior methods have made significant pro…

Seeing Through Circuits: Faithful Mechanistic Interpretability for Vision Transformers

2026-04-15 · Nina Żukowska, Wolfgang Stammer, Bernt Schiele, Jonas Fischer arxiv

Transparency of neural networks' internal reasoning is at the heart of interpretability research, adding to trust, safety, and understanding of these models. The field of mechanistic interpretability has recently focused…

COLEP: Certifiably Robust Learning-Reasoning Conformal Prediction via Probabilistic Circuits

2024-03-17 · Mintong Kang, Nezihe Merve Gürel, Linyi Li, Bo Li

Conformal prediction has shown spurring performance in constructing statistically rigorous prediction sets for arbitrary black-box machine learning models, assuming the data is exchangeable. However, even small adversari…

Conformal Prediction Prediction

Quantifying LLM Attention-Head Stability: Implications for Circuit Universality

2026-02-17 · Karan Bali, Jack Stanley, Praneet Suresh, Danilo Bzdok arxiv

In mechanistic interpretability, recent work scrutinizes transformer "circuits" - sparse, mono or multi layer sub computations, that may reflect human understandable functions. Yet, these network circuits are rarely acid…

On Mechanistic Circuits for Extractive Question-Answering

2025-02-12 · Samyadeep Basu, Vlad Morariu, Zichao Wang, Ryan Rossi 외

Large language models are increasingly used to process documents and facilitate question-answering on them. In our paper, we extract mechanistic circuits for this real-world language modeling task: context-augmented lang…

Extractive Question-Answering Language Modeling Language Modelling Question Answering