Image de couverture de livre

On The Variability of Concept Activation Vectors

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Wenkmann, Julia, Garreau, Damien
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Feature Attribution from First Principles
par: Taimeskhanov, Magamed, et autres
Publié: (2025)

MMD-Flagger: Leveraging Maximum Mean Discrepancy to Detect Hallucinations
par: Mitsuzawa, Kensuke, et autres
Publié: (2025)

Comparing Feature Importance and Rule Extraction for Interpretability on Text Data
par: Lopardo, Gianluigi, et autres
Publié: (2022)

Faithful and Robust Local Interpretability for Textual Predictions
par: Lopardo, Gianluigi, et autres
Publié: (2023)

Towards Understanding Steering Strength
par: Taimeskhanov, Magamed, et autres
Publié: (2026)

GLEAMS: Bridging the Gap Between Local and Global Explanations
par: Visani, Giorgio, et autres
Publié: (2024)

Attention Meets Post-hoc Interpretability: A Mathematical Perspective
par: Lopardo, Gianluigi, et autres
Publié: (2024)

A High-Resolution Landscape Dataset for Concept-Based XAI With Application to Species Distribution Models
par: de la Brosse, Augustin, et autres
Publié: (2026)

Understanding Post-hoc Explainers: The Case of Anchors
par: Lopardo, Gianluigi, et autres
Publié: (2023)

CAM-Based Methods Can See through Walls
par: Taimeskhanov, Magamed, et autres
Publié: (2024)

A Sea of Words: An In-Depth Analysis of Anchors for Text Data
par: Lopardo, Gianluigi, et autres
Publié: (2022)

The Risks of Recourse in Binary Classification
par: Fokkema, Hidde, et autres
Publié: (2023)

Interpretability for Multimodal Emotion Recognition using Concept Activation Vectors
par: Asokan, Ashish Ramayee, et autres
Publié: (2022)

Are Ensembles Getting Better all the Time?
par: Mattei, Pierre-Alexandre, et autres
Publié: (2023)

FastCAV: Efficient Computation of Concept Activation Vectors for Explaining Deep Neural Networks
par: Schmalwasser, Laines, et autres
Publié: (2025)

Concept Boundary Vectors
par: Walker, Thomas
Publié: (2024)

$α$-TCAV: A Unified Framework for Testing with Concept Activation Vectors
par: Schnoor, Ekkehard, et autres
Publié: (2026)

Explainability as statistical inference
par: Senetaire, Hugo Henri Joseph, et autres
Publié: (2022)

Developing Explainable Machine Learning Model using Augmented Concept Activation Vector
par: Hassanpour, Reza, et autres
Publié: (2024)

Navigating Neural Space: Revisiting Concept Activation Vectors to Overcome Directional Divergence
par: Pahde, Frederik, et autres
Publié: (2022)

Explaining Explainability: Recommendations for Effective Use of Concept Activation Vectors
par: Nicolson, Angus, et autres
Publié: (2024)

Vector Quantized Latent Concepts: A Scalable Alternative to Clustering-Based Concept Discovery
par: Yu, Xuemin, et autres
Publié: (2026)

Causality $\neq$ Invariance: Function and Concept Vectors in LLMs
par: Opiełka, Gustaw, et autres
Publié: (2026)

Provable In-Context Vector Arithmetic via Retrieving Task Concepts
par: Bu, Dake, et autres
Publié: (2025)

Beyond Single Concept Vector: Modeling Concept Subspace in LLMs with Gaussian Distribution
par: Zhao, Haiyan, et autres
Publié: (2024)

The SuperActivator Mechanism: Transformers Concentrate Reliable Concept Signals in the Tail
par: Goldberg, Cassandra, et autres
Publié: (2025)

Unsupervised Concept Drift Detection based on Parallel Activations of Neural Network
par: Komorniczak, Joanna, et autres
Publié: (2024)

Stochastic Concept Bottleneck Models
par: Vandenhirtz, Moritz, et autres
Publié: (2024)

Analogical Reasoning Inside Large Language Models: Concept Vectors and the Limits of Abstraction
par: Opiełka, Gustaw, et autres
Publié: (2025)

Concept-Centric Token Interpretation for Vector-Quantized Generative Models
par: Yang, Tianze, et autres
Publié: (2025)

Variable Bitrate Residual Vector Quantization for Audio Coding
par: Chae, Yunkee, et autres
Publié: (2024)

When Are Two Scores Better Than One? Investigating Ensembles of Diffusion Models
par: Razafindralambo, Raphaël, et autres
Publié: (2026)

Beyond Mixtures and Products for Ensemble Aggregation: A Likelihood Perspective on Generalized Means
par: Razafindralambo, Raphaël, et autres
Publié: (2026)

What is Missing? Explaining Neurons Activated by Absent Concepts
par: Hesse, Robin, et autres
Publié: (2026)

Fractional Concepts in Neural Networks: Enhancing Activation Functions
par: Alijani, Zahra, et autres
Publié: (2023)

Fair In-Context Learning via Latent Concept Variables
par: Bhaila, Karuna, et autres
Publié: (2024)

Beyond Steering Vector: Flow-based Activation Steering for Inference-Time Intervention
par: Jin, Zehao, et autres
Publié: (2026)

Interpretable Reward Modeling with Active Concept Bottlenecks
par: Laguna, Sonia, et autres
Publié: (2025)

Post-hoc Stochastic Concept Bottleneck Models
par: Hoffmann, Wiktor Jan, et autres
Publié: (2025)

From Concepts to Components: Concept-Agnostic Attention Module Discovery in Transformers
par: Su, Jingtong, et autres
Publié: (2025)