Image de couverture de livre

Concept Layers: Enhancing Interpretability and Intervenability via LLM Conceptualization

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Bidusa, Or Raphael, Markovitch, Shaul
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning Artificial Intelligence Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Identifying Intervenable and Interpretable Features via Orthogonality Regularization
par: Miller, Moritz, et autres
Publié: (2026)

Cross-Layer Discrete Concept Discovery for Interpreting Language Models
par: Garg, Ankur, et autres
Publié: (2025)

Attention Flows: Tracing LLM Conceptual Engagement via Story Summaries
par: Hicke, Rebecca M. M., et autres
Publié: (2026)

Aligned at the Start: Conceptual Groupings in LLM Embeddings
par: Khatir, Mehrdad, et autres
Publié: (2024)

One Example Shown, Many Concepts Known! Counterexample-Driven Conceptual Reasoning in Mathematical LLMs
par: Li, Yinghui, et autres
Publié: (2025)

Geometry-Lite: Interpretable Safety Probing via Layer-Wise Margin Geometry
par: Sim, Woo Seob, et autres
Publié: (2026)

Variational Language Concepts for Interpreting Foundation Language Models
par: Wang, Hengyi, et autres
Publié: (2024)

Parallel LLM Reasoning for Bias-Resilient, Robust Conceptual Abstraction
par: Adeseye, Aisvarya, et autres
Publié: (2026)

Robustly Improving LLM Fairness in Realistic Settings via Interpretability
par: Karvonen, Adam, et autres
Publié: (2025)

Exploring Concept Depth: How Large Language Models Acquire Knowledge and Concept at Different Layers?
par: Jin, Mingyu, et autres
Publié: (2024)

Interpreting Language Models Through Concept Descriptions: A Survey
par: Feldhus, Nils, et autres
Publié: (2025)

Stories in Space: In-Context Learning Trajectories in Conceptual Belief Space
par: Bigelow, Eric, et autres
Publié: (2026)

Learning to Intervene on Concept Bottlenecks
par: Steinmann, David, et autres
Publié: (2023)

Predictive Concept Decoders: Training Scalable End-to-End Interpretability Assistants
par: Huang, Vincent, et autres
Publié: (2025)

Addressing LLM Diversity by Infusing Random Concepts
par: Agrawal, Pulin, et autres
Publié: (2026)

Geometric Interpretation of Layer Normalization and a Comparative Analysis with RMSNorm
par: Gupta, Akshat, et autres
Publié: (2024)

Adaptive Layer Selection for Layer-Wise Token Pruning in LLM Inference
par: Taniguchi, Rei, et autres
Publié: (2026)

From Isolation to Entanglement: When Do Interpretability Methods Identify and Disentangle Known Concepts?
par: Mueller, Aaron, et autres
Publié: (2025)

Decoding Dark Matter: Specialized Sparse Autoencoders for Interpreting Rare Concepts in Foundation Models
par: Muhamed, Aashiq, et autres
Publié: (2024)

Dr.LLM: Dynamic Layer Routing in LLMs
par: Heakl, Ahmed, et autres
Publié: (2025)

LESA: Learnable LLM Layer Scaling-Up
par: Yang, Yifei, et autres
Publié: (2025)

Thought Branches: Interpreting LLM Reasoning Requires Resampling
par: Macar, Uzay, et autres
Publié: (2025)

Enhancing LLM Reliability via Explicit Knowledge Boundary Modeling
par: Zheng, Hang, et autres
Publié: (2025)

Enhancing LLM Agent Safety via Causal Influence Prompting
par: Hahm, Dongyoon, et autres
Publié: (2025)

Interpreting and Controlling LLM Reasoning through Integrated Policy Gradient
par: Li, Changming, et autres
Publié: (2026)

Interpreting and Controlling Model Behavior via Constitutions for Atomic Concept Edits
par: Kalibhat, Neha, et autres
Publié: (2026)

TrimLLM: Progressive Layer Dropping for Domain-Specific LLMs
par: Hu, Lanxiang, et autres
Publié: (2024)

SAE-V: Interpreting Multimodal Models for Enhanced Alignment
par: Lou, Hantao, et autres
Publié: (2025)

Mechanistic Data Attribution: Tracing the Training Origins of Interpretable LLM Units
par: Chen, Jianhui, et autres
Publié: (2026)

SLM Meets LLM: Balancing Latency, Interpretability and Consistency in Hallucination Detection
par: Hu, Mengya, et autres
Publié: (2024)

LLM-Guided Semantic Bootstrapping for Interpretable Text Classification with Tsetlin Machines
par: Gao, Jiechao, et autres
Publié: (2026)

Joint Detection of Fraud and Concept Drift inOnline Conversations with LLM-Assisted Judgment
par: Senol, Ali, et autres
Publié: (2025)

Adversarial Preference Optimization: Enhancing Your Alignment via RM-LLM Game
par: Cheng, Pengyu, et autres
Publié: (2023)

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

StateAct: Enhancing LLM Base Agents via Self-prompting and State-tracking
par: Rozanov, Nikolai, et autres
Publié: (2024)

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision
par: Xi, Zhiheng, et autres
Publié: (2024)

MaskPrune: Mask-based LLM Pruning for Layer-wise Uniform Structures
par: Qin, Jiayu, et autres
Publié: (2025)

DiagnoLLM: A Hybrid Bayesian Neural Language Framework for Interpretable Disease Diagnosis
par: Xu, Bowen, et autres
Publié: (2025)

Logical Structure as Knowledge: Enhancing LLM Reasoning via Structured Logical Knowledge Density Estimation
par: Bi, Zhen, et autres
Publié: (2025)

Enhancing LLM Evaluations: The Garbling Trick
par: Bradley, William F.
Publié: (2024)