Imagen de Portada

InverseScope: Scalable Activation Inversion for Interpreting Large Language Models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Luo, Yifan, Zhou, Zhennan, Dong, Bin
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

An Interpretable and Scalable Framework for Evaluating Large Language Models
por: Qu, Xinhao, et al.
Publicado: (2026)

Interpretable Steering of Large Language Models with Feature Guided Activation Additions
por: Soo, Samuel, et al.
Publicado: (2025)

GWT: Scalable Optimizer State Compression for Large Language Model Training
por: Wen, Ziqing, et al.
Publicado: (2025)

Distributed Interpretability and Control for Large Language Models
por: Desai, Dev Arpan, et al.
Publicado: (2026)

Inverse-RLignment: Large Language Model Alignment from Demonstrations through Inverse Reinforcement Learning
por: Sun, Hao, et al.
Publicado: (2024)

From Projection to Prediction: Beyond Logits for Scalable Language Models
por: Dong, Jianbing, et al.
Publicado: (2025)

Steering Large Language Model Activations in Sparse Spaces
por: Bayat, Reza, et al.
Publicado: (2025)

Medical Interpretability and Knowledge Maps of Large Language Models
por: Marinescu, Razvan, et al.
Publicado: (2025)

TS-Inverse: A Gradient Inversion Attack Tailored for Federated Time Series Forecasting Models
por: Meijer, Caspar, et al.
Publicado: (2025)

DLM-Scope: Mechanistic Interpretability of Diffusion Language Models via Sparse Autoencoders
por: Wang, Xu, et al.
Publicado: (2026)

Activation Sparsity Opportunities for Compressing General Large Language Models
por: Dhar, Nobel, et al.
Publicado: (2024)

Imitating Language via Scalable Inverse Reinforcement Learning
por: Wulfmeier, Markus, et al.
Publicado: (2024)

Towards Machine Theory of Mind with Large Language Model-Augmented Inverse Planning
por: Gelpí, Rebekah A., et al.
Publicado: (2025)

Interpretable Operator Learning for Inverse Problems via Adaptive Spectral Filtering: Convergence and Discretization Invariance
por: Dong, Hang-Cheng, et al.
Publicado: (2026)

Polynomial Composition Activations: Unleashing the Dynamics of Large Language Models
por: Zhuo, Zhijian, et al.
Publicado: (2024)

ASER: Activation Smoothing and Error Reconstruction for Large Language Model Quantization
por: Zhao, Weibo, et al.
Publicado: (2024)

Inverse Flow and Consistency Models
por: Zhang, Yuchen, et al.
Publicado: (2025)

Towards Interpretable Deep Reinforcement Learning Models via Inverse Reinforcement Learning
por: Xie, Sean, et al.
Publicado: (2022)

WINA: Weight Informed Neuron Activation for Accelerating Large Language Model Inference
por: Chen, Sihan, et al.
Publicado: (2025)

Uncovering Gradient Inversion Risks in Practical Language Model Training
por: Feng, Xinguo, et al.
Publicado: (2025)

Uncovering Scaling Laws for Large Language Models via Inverse Problems
por: Verma, Arun, et al.
Publicado: (2025)

REMA: A Unified Reasoning Manifold Framework for Interpreting Large Language Model
por: Li, Bo, et al.
Publicado: (2025)

Using Mechanistic Interpretability to Craft Adversarial Attacks against Large Language Models
por: Winninger, Thomas, et al.
Publicado: (2025)

Rethinking Interpretability in the Era of Large Language Models
por: Singh, Chandan, et al.
Publicado: (2024)

A Survey on Sparse Autoencoders: Interpreting the Internal Mechanisms of Large Language Models
por: Shu, Dong, et al.
Publicado: (2025)

Position: What Can Large Language Models Tell Us about Time Series Analysis
por: Jin, Ming, et al.
Publicado: (2024)

IDLM: Inverse-distilled Diffusion Language Models
por: Li, David, et al.
Publicado: (2026)

Model Inversion Attacks on Llama 3: Extracting PII from Large Language Models
por: Sivashanmugam, Sathesh P.
Publicado: (2025)

Scalable Efficient Training of Large Language Models with Low-dimensional Projected Attention
por: Lv, Xingtai, et al.
Publicado: (2024)

Prototype Training with Dual Pseudo-Inverse and Optimized Hidden Activations
por: Tucci, Mauro
Publicado: (2025)

Bridging Large Language Models and Graph Structure Learning Models for Robust Representation Learning
por: Su, Guangxin, et al.
Publicado: (2024)

Reducing the Scope of Language Models
por: Yunis, David, et al.
Publicado: (2024)

QuZO: Quantized Zeroth-Order Fine-Tuning for Large Language Models
por: Zhou, Jiajun, et al.
Publicado: (2025)

LEPO: Latent Reasoning Policy Optimization for Large Language Models
por: Zhou, Yuyan, et al.
Publicado: (2026)

Spectral Editing of Activations for Large Language Model Alignment
por: Qiu, Yifu, et al.
Publicado: (2024)

Conda: Column-Normalized Adam for Training Large Language Models Faster
por: Wang, Junjie, et al.
Publicado: (2025)

Binary Autoencoder for Mechanistic Interpretability of Large Language Models
por: Cho, Hakaze, et al.
Publicado: (2025)

Learning Interpretable Rules for Scalable Data Representation and Classification
por: Wang, Zhuo, et al.
Publicado: (2023)

Amber Pruner: Leveraging N:M Activation Sparsity for Efficient Prefill in Large Language Models
por: An, Tai, et al.
Publicado: (2025)

MLLMEraser: Achieving Test-Time Unlearning in Multimodal Large Language Models through Activation Steering
por: Ding, Chenlu, et al.
Publicado: (2025)