Imagen de Portada

Cyclic Ablation: Testing Concept Localization against Functional Regeneration in AI

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autor principal:	Kapelko, Eduard
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Active Inference Agency Formalization, Metrics, and Convergence Assessments
por: Kapelko, Eduard
Publicado: (2026)

Steering Out-of-Distribution Generalization with Concept Ablation Fine-Tuning
por: Casademunt, Helena, et al.
Publicado: (2025)

Causality $\neq$ Invariance: Function and Concept Vectors in LLMs
por: Opiełka, Gustaw, et al.
Publicado: (2026)

Functional Component Ablation Reveals Specialization Patterns in Hybrid Language Model Architectures
por: Borobia, Hector, et al.
Publicado: (2026)

Circuit Breaking: Removing Model Behaviors with Targeted Ablation
por: Li, Maximilian, et al.
Publicado: (2023)

Scalable Data Ablation Approximations for Language Models through Modular Training and Merging
por: Na, Clara, et al.
Publicado: (2024)

Do LLMs Understand Romanian Driving Laws? A Study on Multimodal and Fine-Tuned Question Answering
por: Barbu, Eduard, et al.
Publicado: (2025)

MedConceptsQA: Open Source Medical Concepts QA Benchmark
por: Shoham, Ofir Ben, et al.
Publicado: (2024)

Kernelized Concept Erasure
por: Ravfogel, Shauli, et al.
Publicado: (2022)

Vector Quantized Latent Concepts: A Scalable Alternative to Clustering-Based Concept Discovery
por: Yu, Xuemin, et al.
Publicado: (2026)

LLM Pretraining with Continuous Concepts
por: Tack, Jihoon, et al.
Publicado: (2025)

Towards Compositionality in Concept Learning
por: Stein, Adam, et al.
Publicado: (2024)

Linear Adversarial Concept Erasure
por: Ravfogel, Shauli, et al.
Publicado: (2022)

LCSB: Layer-Cyclic Selective Backpropagation for Memory-Efficient On-Device LLM Fine-Tuning
por: Park, Juneyoung, et al.
Publicado: (2026)

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

Data Alignment for Zero-Shot Concept Generation in Dermatology AI
por: Gadgil, Soham, et al.
Publicado: (2024)

AlignSAE: Concept-Aligned Sparse Autoencoders
por: Yang, Minglai, et al.
Publicado: (2025)

Leveraging AI Graders for Missing Score Imputation to Achieve Accurate Ability Estimation in Constructed-Response Tests
por: Uto, Masaki, et al.
Publicado: (2025)

Simple Mechanisms for Representing, Indexing and Manipulating Concepts
por: Li, Yuanzhi, et al.
Publicado: (2023)

Beyond Individual Facts: Investigating Categorical Knowledge Locality of Taxonomy and Meronomy Concepts in GPT Models
por: Burger, Christopher, et al.
Publicado: (2024)

Nonlinear Concept Erasure: a Density Matching Approach
por: Saillenfest, Antoine, et al.
Publicado: (2025)

Evaluating Sparse Autoencoders on Targeted Concept Erasure Tasks
por: Karvonen, Adam, et al.
Publicado: (2024)

Khattat: Enhancing Readability and Concept Representation of Semantic Typography
por: Hussein, Ahmed, et al.
Publicado: (2024)

Medical Concept Normalization in a Low-Resource Setting
por: Patzelt, Tim
Publicado: (2024)

Learning Machines: In Search of a Concept Oriented Language
por: Gunes, Veyis
Publicado: (2024)

Evaluating Defences against Unsafe Feedback in RLHF
por: Rosati, Domenic, et al.
Publicado: (2024)

Trained on Tokens, Calibrated on Concepts: The Emergence of Semantic Calibration in LLMs
por: Nakkiran, Preetum, et al.
Publicado: (2025)

Visual Exploration of Feature Relationships in Sparse Autoencoders with Curated Concepts
por: Yan, Xinyuan, et al.
Publicado: (2025)

Concept Algebra for (Score-Based) Text-Controlled Generative Models
por: Wang, Zihao, et al.
Publicado: (2023)

Can LLMs Learn New Concepts Incrementally without Forgetting?
por: Zheng, Junhao, et al.
Publicado: (2024)

CLUE: Concept-Level Uncertainty Estimation for Large Language Models
por: Wang, Yu-Hsiang, et al.
Publicado: (2024)

TempTest: Local Normalization Distortion and the Detection of Machine-generated Text
por: Kempton, Tom, et al.
Publicado: (2025)

MesaNet: Sequence Modeling by Locally Optimal Test-Time Training
por: von Oswald, Johannes, et al.
Publicado: (2025)

The more polypersonal the better -- a short look on space geometry of fine-tuned layers
por: Kudriashov, Sergei, et al.
Publicado: (2025)

Automated Knowledge Concept Annotation and Question Representation Learning for Knowledge Tracing
por: Ozyurt, Yilmazcan, et al.
Publicado: (2024)

Interactive Dialogue Agents via Reinforcement Learning on Hindsight Regenerations
por: Hong, Joey, et al.
Publicado: (2024)

Concept Tokens: Learning Behavioral Embeddings Through Concept Definitions
por: Sastre, Ignacio, et al.
Publicado: (2026)

Adversarial Evasion Attack Efficiency against Large Language Models
por: Vitorino, João, et al.
Publicado: (2024)

Analogical Reasoning Inside Large Language Models: Concept Vectors and the Limits of Abstraction
por: Opiełka, Gustaw, et al.
Publicado: (2025)

Concept Unlearning in Large Language Models via Self-Constructed Knowledge Triplets
por: Yamashita, Tomoya, et al.
Publicado: (2025)