Cover Image

Concept Component Analysis: A Principled Approach for Concept Extraction in LLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Liu, Yuhang, Gao, Erdun, Gong, Dong, Hengel, Anton van den, Shi, Javen Qinfeng
Format:	Preprint
Published:	2026
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

I Predict Therefore I Am: Is Next Token Prediction Enough to Learn Human-Interpretable Concepts from Data?
by: Liu, Yuhang, et al.
Published: (2025)

Towards Identifiable Latent Additive Noise Models
by: Liu, Yuhang, et al.
Published: (2024)

On the Value of Cross-Modal Misalignment in Multimodal Representation Learning
by: Cai, Yichao, et al.
Published: (2025)

Beyond DAGs: A Latent Partial Causal Model for Multimodal Learning
by: Liu, Yuhang, et al.
Published: (2024)

Identifiable Latent Polynomial Causal Models Through the Lens of Change
by: Liu, Yuhang, et al.
Published: (2023)

Identifying Weight-Variant Latent Causal Models
by: Liu, Yuhang, et al.
Published: (2022)

Latent Covariate Shift: Unlocking Partial Identifiability for Multi-Source Domain Adaptation
by: Liu, Yuhang, et al.
Published: (2022)

Learning Latent Dynamical Causal Processes for Single-Cell Perturbation Prediction
by: Jiang, Wenkang, et al.
Published: (2026)

Chem4DLLM: 4D Multimodal LLMs for Chemical Dynamics Understanding
by: Li, Xinyu, et al.
Published: (2026)

Analytic DAG Constraints for Differentiable DAG Learning
by: Zhang, Zhen, et al.
Published: (2025)

What Makes a Representation Good for Single-Cell Perturbation Prediction?
by: Jiang, Wenkang, et al.
Published: (2026)

Rethinking State Disentanglement in Causal Reinforcement Learning
by: Cao, Haiyao, et al.
Published: (2024)

A Survey on Deep Neural Network Pruning-Taxonomy, Comparison, Analysis, and Recommendations
by: Cheng, Hongrong, et al.
Published: (2023)

The Geometric Mechanics of Contrastive Representation Learning: Alignment Potentials, Entropic Dispersion, and Cross-modal Divergence
by: Cai, Yichao, et al.
Published: (2026)

Premonition: Using Generative Models to Preempt Future Data Changes in Continual Learning
by: McDonnell, Mark D., et al.
Published: (2024)

InvariantStock: Learning Invariant Features for Mastering the Shifting Market
by: Cao, Haiyao, et al.
Published: (2024)

Interactive Medical Image Analysis with Concept-based Similarity Reasoning
by: Huy, Ta Duc, et al.
Published: (2025)

Confident Sinkhorn Allocation for Pseudo-Labeling
by: Nguyen, Vu, et al.
Published: (2022)

ActiveCQ: Active Estimation of Causal Quantities
by: Gao, Erdun, et al.
Published: (2025)

RanPAC: Random Projections and Pre-trained Models for Continual Learning
by: McDonnell, Mark D., et al.
Published: (2023)

Transformers Pretrained on Procedural Data Contain Modular Structures for Algorithmic Reasoning
by: Shinnick, Zachary, et al.
Published: (2025)

Causal-EPIG: A Prediction-Oriented Active Learning Framework for CATE Estimation
by: Gao, Erdun, et al.
Published: (2025)

Procedural Pretraining: Warming Up Language Models with Abstract Data
by: Jiang, Liangze, et al.
Published: (2026)

Concept Extraction for Time Series with ECLAD-ts
by: Holzapfel, Antonia, et al.
Published: (2025)

Provably Efficient Bayesian Optimization with Unknown Gaussian Process Hyperparameter Estimation
by: Ha, Huong, et al.
Published: (2023)

Highway Graph to Accelerate Reinforcement Learning
by: Yin, Zidu, et al.
Published: (2024)

From Concepts to Components: Concept-Agnostic Attention Module Discovery in Transformers
by: Su, Jingtong, et al.
Published: (2025)

The Devil is in the Distributions: Explicit Modeling of Scene Content is Key in Zero-Shot Video Captioning
by: Tian, Mingkai, et al.
Published: (2025)

Composite Concept Extraction through Backdooring
by: Ghosh, Banibrata, et al.
Published: (2024)

Sample-efficient Learning of Concepts with Theoretical Guarantees: from Data to Concepts without Interventions
by: Fokkema, Hidde, et al.
Published: (2025)

Engineering Resource-constrained Software Systems with DNN Components: a Concept-based Pruning Approach
by: Formica, Federico, et al.
Published: (2026)

Towards Higher Effective Rank in Parameter-efficient Fine-tuning using Khatri--Rao Product
by: Albert, Paul, et al.
Published: (2025)

Beyond Single Concept Vector: Modeling Concept Subspace in LLMs with Gaussian Distribution
by: Zhao, Haiyan, et al.
Published: (2024)

An Axiomatic Approach to Model-Agnostic Concept Explanations
by: Feng, Zhili, et al.
Published: (2024)

ConceptTracer: Interactive Analysis of Concept Saliency and Selectivity in Neural Representations
by: Knauer, Ricardo, et al.
Published: (2026)

Diverse Concept Proposals for Concept Bottleneck Models
by: Brown, Katrina, et al.
Published: (2024)

MCCE: Missingness-aware Causal Concept Explainer
by: Gao, Jifan, et al.
Published: (2024)

Observationally Informed Adaptive Causal Experimental Design
by: Gao, Erdun, et al.
Published: (2026)

Causal Explanation of Concept Drift -- A Truly Actionable Approach
by: Komnick, David, et al.
Published: (2025)

Decomposing Task Vectors for Refined Model Editing
by: Damirchi, Hamed, et al.
Published: (2025)