Image de couverture de livre

Command-V: Pasting LLM Behaviors via Activation Profiles

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Wang, Barry, Schwarzschild, Avi, Robey, Alexander, Payani, Ali, Fleming, Charles, Sun, Mingjie, Ippolito, Daphne
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Forcing Diffuse Distributions out of Language Models
par: Zhang, Yiming, et autres
Publié: (2024)

Existing Large Language Model Unlearning Evaluations Are Inconclusive
par: Feng, Zhili, et autres
Publié: (2025)

Algorithms for Adversarially Robust Deep Learning
par: Robey, Alexander
Publié: (2025)

Benchmarking ChatGPT on Algorithmic Reasoning
par: McLeish, Sean, et autres
Publié: (2024)

Rethinking LLM Memorization through the Lens of Adversarial Compression
par: Schwarzschild, Avi, et autres
Publié: (2024)

Beyond Semantic Entropy: Boosting LLM Uncertainty Quantification with Pairwise Semantic Similarity
par: Nguyen, Dang, et autres
Publié: (2025)

Universal Activation Verbalizer: A Unified Framework for Cross-Model Activation Explanation
par: Zhao, Haiyan, et autres
Publié: (2026)

Easy2Hard-Bench: Standardized Difficulty Labels for Profiling LLM Performance and Generalization
par: Ding, Mucong, et autres
Publié: (2024)

Self-Improving Transformers Overcome Easy-to-Hard and Length Generalization Challenges
par: Lee, Nayoung, et autres
Publié: (2025)

Prompt Recovery for Image Generation Models: A Comparative Study of Discrete Optimizers
par: Williams, Joshua Nathaniel, et autres
Publié: (2024)

SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks
par: Robey, Alexander, et autres
Publié: (2023)

Generalization Error Bounds for Learning under Censored Feedback
par: Yang, Yifan, et autres
Publié: (2024)

TOFU: A Task of Fictitious Unlearning for LLMs
par: Maini, Pratyush, et autres
Publié: (2024)

When is Tree Search Useful for LLM Planning? It Depends on the Discriminator
par: Chen, Ziru, et autres
Publié: (2024)

Friends in Unexpected Places: Enhancing Local Fairness in Federated Learning through Clustering
par: Yang, Yifan, et autres
Publié: (2024)

FictionalQA: A Dataset for Studying Memorization and Knowledge Acquisition
par: Kirchenbauer, John, et autres
Publié: (2025)

Provable tradeoffs in adversarially robust classification
par: Dobriban, Edgar, et autres
Publié: (2020)

Weight Updates as Activation Shifts: A Principled Framework for Steering
par: Adila, Dyah, et autres
Publié: (2026)

Human-aligned Chess with a Bit of Search
par: Zhang, Yiming, et autres
Publié: (2024)

SafeSwitch: Steering Unsafe LLM Behavior via Internal Activation Signals
par: Han, Peixuan, et autres
Publié: (2025)

Steering Dialogue Dynamics for Robustness against Multi-turn Jailbreaking Attacks
par: Hu, Hanjiang, et autres
Publié: (2025)

Personalized Federated Fine-tuning for Heterogeneous Data: An Automatic Rank Learning Approach via Two-Level LoRA
par: Hao, Jie, et autres
Publié: (2025)

Massive Activations in Large Language Models
par: Sun, Mingjie, et autres
Publié: (2024)

FBI-LLM: Scaling Up Fully Binarized LLMs from Scratch via Autoregressive Distillation
par: Ma, Liqun, et autres
Publié: (2024)

Measuring Non-Adversarial Reproduction of Training Data in Large Language Models
par: Aerni, Michael, et autres
Publié: (2024)

A Generic Framework for Conformal Fairness
par: Vadlamani, Aditya T., et autres
Publié: (2025)

Towards Strong Certified Defense with Universal Asymmetric Randomization
par: Hong, Hanbin, et autres
Publié: (2025)

Evaluating Language Model Reasoning about Confidential Information
par: Sam, Dylan, et autres
Publié: (2025)

When Should We Introduce Safety Interventions During Pretraining?
par: Sam, Dylan, et autres
Publié: (2026)

Program Semantic Inequivalence Game with Large Language Models
par: Miceli-Barone, Antonio Valerio, et autres
Publié: (2025)

Spotting LLMs With Binoculars: Zero-Shot Detection of Machine-Generated Text
par: Hans, Abhimanyu, et autres
Publié: (2024)

Data-Efficient Contrastive Language-Image Pretraining: Prioritizing Data Quality over Quantity
par: Joshi, Siddharth, et autres
Publié: (2024)

Predicting Plasticity in Deep Continual Learning: A Theoretical Perspective
par: Wang, Jiuqi, et autres
Publié: (2026)

SpikCommander: A High-performance Spiking Transformer with Multi-view Learning for Efficient Speech Command Recognition
par: Wang, Jiaqi, et autres
Publié: (2025)

Rep2Text: Decoding Full Text from a Single LLM Token Representation
par: Zhao, Haiyan, et autres
Publié: (2025)

Language Ranker: A Metric for Quantifying LLM Performance Across High and Low-Resource Languages
par: Li, Zihao, et autres
Publié: (2024)

Conformal Prediction: A Theoretical Note and Benchmarking Transductive Node Classification in Graphs
par: Maneriker, Pranav, et autres
Publié: (2024)

Anonymous-by-Construction: An LLM-Driven Framework for Privacy-Preserving Text
par: Albanese, Federico, et autres
Publié: (2026)

Chordal Sparsity for Lipschitz Constant Estimation of Deep Neural Networks
par: Xue, Anton, et autres
Publié: (2022)

BPE: Behavioral Profiling Ensemble
par: Liu, Yanxin, et autres
Publié: (2026)