Cover Image

Evaluating Neuron Explanations: A Unified Framework with Sanity Checks

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Oikarinen, Tuomas, Yan, Ge, Weng, Tsui-Wei
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Faithful and Stable Neuron Explanations for Trustworthy Mechanistic Interpretability
by: Yan, Ge, et al.
Published: (2025)

Linear Explanations for Individual Neurons
by: Oikarinen, Tuomas, et al.
Published: (2024)

Beyond Top Activations: Efficient and Reliable Crowdsourced Evaluation of Automated Interpretability
by: Oikarinen, Tuomas, et al.
Published: (2025)

Crafting Large Language Models for Enhanced Interpretability
by: Sun, Chung-En, et al.
Published: (2024)

Interpreting Neurons in Deep Vision Networks with Language Models
by: Bai, Nicholas, et al.
Published: (2024)

Sanity Checks for Explanation Uncertainty
by: Valdenegro-Toro, Matias, et al.
Published: (2024)

Interpretable Generative Models through Post-hoc Concept Bottlenecks
by: Kulkarni, Akshay, et al.
Published: (2025)

CI-CBM: Class-Incremental Concept Bottleneck Model for Interpretable Continual Learning
by: Javadi, Amirhosein, et al.
Published: (2026)

Concept Bottleneck Large Language Models
by: Sun, Chung-En, et al.
Published: (2024)

Sanity Checks for Agentic Data Science
by: Rewolinski, Zachary T., et al.
Published: (2026)

Are LLM Evaluators Really Narcissists? Sanity Checking Self-Preference Evaluations
by: Roytburg, Dani, et al.
Published: (2026)

RAT: Boosting Misclassification Detection Ability without Extra Data
by: Yan, Ge, et al.
Published: (2025)

Sanity Checks for Sparse Autoencoders: Do SAEs Beat Random Baselines?
by: Korznikov, Anton, et al.
Published: (2026)

A Fresh Look at Sanity Checks for Saliency Maps
by: Hedström, Anna, et al.
Published: (2024)

VLG-CBM: Training Concept Bottleneck Models with Vision-Language Guidance
by: Srivastava, Divyansh, et al.
Published: (2024)

Sanity Checks Revisited: An Exploration to Repair the Model Parameter Randomisation Test
by: Hedström, Anna, et al.
Published: (2024)

ThinkEdit: Interpretable Weight Editing to Mitigate Overly Short Thinking in Reasoning Models
by: Sun, Chung-En, et al.
Published: (2025)

Provably Robust Conformal Prediction with Improved Efficiency
by: Yan, Ge, et al.
Published: (2024)

Sanity Checking Causal Representation Learning on a Simple Real-World System
by: Gamella, Juan L., et al.
Published: (2025)

Resting Neurons, Active Insights: Robustifying Activation Sparsity in LLMs via Spontaneity
by: Xu, Haotian, et al.
Published: (2025)

Towards a Unified Framework for Evaluating Explanations
by: Pinto, Juan D., et al.
Published: (2024)

Interpretability-Guided Test-Time Adversarial Defense
by: Kulkarni, Akshay, et al.
Published: (2024)

CoSy: Evaluating Textual Explanations of Neurons
by: Kopf, Laura, et al.
Published: (2024)

Distance Marching for Generative Modeling
by: Wang, Zimo, et al.
Published: (2026)

Effective Skill Unlearning through Intervention and Abstention
by: Li, Yongce, et al.
Published: (2025)

Breaking the Barrier: Enhanced Utility and Robustness in Smoothed DRL Agents
by: Sun, Chung-En, et al.
Published: (2024)

Graph Concept Bottleneck Models
by: Xu, Haotian, et al.
Published: (2025)

Prediction without Preclusion: Recourse Verification with Reachable Sets
by: Kothari, Avni, et al.
Published: (2023)

Abstracted Shapes as Tokens -- A Generalizable and Interpretable Model for Time-series Classification
by: Wen, Yunshi, et al.
Published: (2024)

Statistical Inference for Responsiveness Verification
by: Cheon, Seung Hyun, et al.
Published: (2025)

Understanding Fixed Predictions via Confined Regions
by: Lawless, Connor, et al.
Published: (2025)

Universal Activation Verbalizer: A Unified Framework for Cross-Model Activation Explanation
by: Zhao, Haiyan, et al.
Published: (2026)

A Unified Evaluation Framework for Epistemic Predictions
by: Manchingal, Shireen Kudukkil, et al.
Published: (2025)

Guaranteed Optimal Compositional Explanations for Neurons
by: La Rosa, Biagio, et al.
Published: (2025)

Beyond Attribution: Unified Concept-Level Explanations
by: Liu, Junhao, et al.
Published: (2024)

Unified Explanations in Machine Learning Models: A Perturbation Approach
by: Dineen, Jacob, et al.
Published: (2024)

Probabilistic Federated Prompt-Tuning with Non-IID and Imbalanced Data
by: Weng, Pei-Yau, et al.
Published: (2025)

DeepFaith: A Domain-Free and Model-Agnostic Unified Framework for Highly Faithful Explanations
by: Guo, Yuhan, et al.
Published: (2025)

Open Vocabulary Compositional Explanations for Neuron Alignment
by: La Rosa, Biagio, et al.
Published: (2025)

A Sanity Check for AI-generated Image Detection
by: Yan, Shilin, et al.
Published: (2024)