Cover Image

Universal Activation Verbalizer: A Unified Framework for Cross-Model Activation Explanation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhao, Haiyan, He, Zirui, Wang, Guanchu, Payani, Ali, Li, Yingcong, Du, Mengnan
Format:	Preprint
Published:	2026
Subjects:	Computation and Language Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

SAIF: A Sparse Autoencoder Framework for Interpreting and Steering Instruction Following of Language Models
by: He, Zirui, et al.
Published: (2025)

LogitTrace: Detecting Benchmark Contamination via Layerwise Logit Trajectories
by: He, Zirui, et al.
Published: (2025)

Rep2Text: Decoding Full Text from a Single LLM Token Representation
by: Zhao, Haiyan, et al.
Published: (2025)

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

Beyond Input Activations: Identifying Influential Latents by Gradient Sparse Autoencoders
by: Shu, Dong, et al.
Published: (2025)

Exploring Multilingual Probing in Large Language Models: A Cross-Language Analysis
by: Li, Daoyang, et al.
Published: (2024)

Language Ranker: A Metric for Quantifying LLM Performance Across High and Low-Resource Languages
by: Li, Zihao, et al.
Published: (2024)

NeuronScope: A Multi-Agent Framework for Explaining Polysemantic Neurons in Language Models
by: Liu, Weiqi, et al.
Published: (2026)

FaithLM: Towards Faithful Explanations for Large Language Models
by: Chuang, Yu-Neng, et al.
Published: (2024)

Do Activation Verbalization Methods Convey Privileged Information?
by: Li, Millicent, et al.
Published: (2025)

SAE-FiRE: Enhancing Earnings Surprise Predictions Through Sparse Autoencoder Feature Selection
by: Zhang, Huopu, et al.
Published: (2025)

SAE-SSV: Supervised Steering in Sparse Representation Spaces for Reliable Control of Language Models
by: He, Zirui, et al.
Published: (2025)

Verbal Werewolf: Engage Users with Verbalized Agentic Werewolf Game Framework
by: Fan, Qihui, et al.
Published: (2025)

Beyond Semantic Entropy: Boosting LLM Uncertainty Quantification with Pairwise Semantic Similarity
by: Nguyen, Dang, et al.
Published: (2025)

AdaJudge: Adaptive Multi-Perspective Judging for Reward Modeling
by: Miao, Yongliang, et al.
Published: (2026)

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

Reasoning-preserved Efficient Distillation of Large Language Models via Activation-aware Initialization
by: He, Junlin, et al.
Published: (2026)

First Activations Matter: Training-Free Methods for Dynamic Activation in Large Language Models
by: Ma, Chi, et al.
Published: (2024)

Exploring Activation Patterns of Parameters in Language Models
by: Wang, Yudong, et al.
Published: (2024)

Large Vision-Language Model Alignment and Misalignment: A Survey Through the Lens of Explainability
by: Shu, Dong, et al.
Published: (2025)

Feature Extraction and Steering for Enhanced Chain-of-Thought Reasoning in Language Models
by: Li, Zihao, et al.
Published: (2025)

DBR: Divergence-Based Regularization for Debiasing Natural Language Understanding Models
by: Li, Zihao, et al.
Published: (2025)

FishBack: Pullback Fisher Geometry for Optimal Activation Steering in Transformers
by: Wang, Sihan, et al.
Published: (2026)

Comparative Analysis of Demonstration Selection Algorithms for LLM In-Context Learning
by: Shu, Dong, et al.
Published: (2024)

Supervised Fine-Tuning Achieve Rapid Task Adaption Via Alternating Attention Head Activation Patterns
by: Zhao, Yang, et al.
Published: (2024)

Massive Activations in Large Language Models
by: Sun, Mingjie, et al.
Published: (2024)

Steering Language Models With Activation Engineering
by: Turner, Alexander Matt, et al.
Published: (2023)

Winner-Take-All Column Row Sampling for Memory Efficient Adaptation of Language Model
by: Liu, Zirui, et al.
Published: (2023)

Personalized Federated Fine-tuning for Heterogeneous Data: An Automatic Rank Learning Approach via Two-Level LoRA
by: Hao, Jie, et al.
Published: (2025)

Strategic Demonstration Selection for Improved Fairness in LLM In-Context Learning
by: Hu, Jingyu, et al.
Published: (2024)

DTS: Enhancing Large Reasoning Models via Decoding Tree Sketching
by: Xu, Zicheng, et al.
Published: (2025)

Q-Sparse: All Large Language Models can be Fully Sparsely-Activated
by: Wang, Hongyu, et al.
Published: (2024)

Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models
by: Zhao, Zekai, et al.
Published: (2025)

Communicating Activations Between Language Model Agents
by: Ramesh, Vignav, et al.
Published: (2025)

Mitigating the Impact of Outlier Channels for Language Model Quantization with Activation Regularization
by: Nrusimha, Aniruddha, et al.
Published: (2024)

Steering MoE LLMs via Expert (De)Activation
by: Fayyaz, Mohsen, et al.
Published: (2025)

Similarity-Distance-Magnitude Activations
by: Schmaltz, Allen
Published: (2025)

Fine-Grained Interpretation of Political Opinions in Large Language Models
by: Hu, Jingyu, et al.
Published: (2025)

Few-shot Adaptation to Distribution Shifts By Mixing Source and Target Embeddings
by: Xue, Yihao, et al.
Published: (2023)

Spherical Steering: Geometry-Aware Activation Rotation for Language Models
by: You, Zejia, et al.
Published: (2026)