Copertina

Command-V: Pasting LLM Behaviors via Activation Profiles

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Wang, Barry, Schwarzschild, Avi, Robey, Alexander, Payani, Ali, Fleming, Charles, Sun, Mingjie, Ippolito, Daphne
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Forcing Diffuse Distributions out of Language Models
di: Zhang, Yiming, et al.
Pubblicazione: (2024)

Existing Large Language Model Unlearning Evaluations Are Inconclusive
di: Feng, Zhili, et al.
Pubblicazione: (2025)

Algorithms for Adversarially Robust Deep Learning
di: Robey, Alexander
Pubblicazione: (2025)

Benchmarking ChatGPT on Algorithmic Reasoning
di: McLeish, Sean, et al.
Pubblicazione: (2024)

Rethinking LLM Memorization through the Lens of Adversarial Compression
di: Schwarzschild, Avi, et al.
Pubblicazione: (2024)

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

Universal Activation Verbalizer: A Unified Framework for Cross-Model Activation Explanation
di: Zhao, Haiyan, et al.
Pubblicazione: (2026)

Easy2Hard-Bench: Standardized Difficulty Labels for Profiling LLM Performance and Generalization
di: Ding, Mucong, et al.
Pubblicazione: (2024)

Self-Improving Transformers Overcome Easy-to-Hard and Length Generalization Challenges
di: Lee, Nayoung, et al.
Pubblicazione: (2025)

Prompt Recovery for Image Generation Models: A Comparative Study of Discrete Optimizers
di: Williams, Joshua Nathaniel, et al.
Pubblicazione: (2024)

SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks
di: Robey, Alexander, et al.
Pubblicazione: (2023)

Generalization Error Bounds for Learning under Censored Feedback
di: Yang, Yifan, et al.
Pubblicazione: (2024)

TOFU: A Task of Fictitious Unlearning for LLMs
di: Maini, Pratyush, et al.
Pubblicazione: (2024)

When is Tree Search Useful for LLM Planning? It Depends on the Discriminator
di: Chen, Ziru, et al.
Pubblicazione: (2024)

Friends in Unexpected Places: Enhancing Local Fairness in Federated Learning through Clustering
di: Yang, Yifan, et al.
Pubblicazione: (2024)

FictionalQA: A Dataset for Studying Memorization and Knowledge Acquisition
di: Kirchenbauer, John, et al.
Pubblicazione: (2025)

Provable tradeoffs in adversarially robust classification
di: Dobriban, Edgar, et al.
Pubblicazione: (2020)

Weight Updates as Activation Shifts: A Principled Framework for Steering
di: Adila, Dyah, et al.
Pubblicazione: (2026)

Human-aligned Chess with a Bit of Search
di: Zhang, Yiming, et al.
Pubblicazione: (2024)

SafeSwitch: Steering Unsafe LLM Behavior via Internal Activation Signals
di: Han, Peixuan, et al.
Pubblicazione: (2025)

Steering Dialogue Dynamics for Robustness against Multi-turn Jailbreaking Attacks
di: Hu, Hanjiang, et al.
Pubblicazione: (2025)

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

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

FBI-LLM: Scaling Up Fully Binarized LLMs from Scratch via Autoregressive Distillation
di: Ma, Liqun, et al.
Pubblicazione: (2024)

Measuring Non-Adversarial Reproduction of Training Data in Large Language Models
di: Aerni, Michael, et al.
Pubblicazione: (2024)

A Generic Framework for Conformal Fairness
di: Vadlamani, Aditya T., et al.
Pubblicazione: (2025)

Towards Strong Certified Defense with Universal Asymmetric Randomization
di: Hong, Hanbin, et al.
Pubblicazione: (2025)

Evaluating Language Model Reasoning about Confidential Information
di: Sam, Dylan, et al.
Pubblicazione: (2025)

When Should We Introduce Safety Interventions During Pretraining?
di: Sam, Dylan, et al.
Pubblicazione: (2026)

Program Semantic Inequivalence Game with Large Language Models
di: Miceli-Barone, Antonio Valerio, et al.
Pubblicazione: (2025)

Spotting LLMs With Binoculars: Zero-Shot Detection of Machine-Generated Text
di: Hans, Abhimanyu, et al.
Pubblicazione: (2024)

Data-Efficient Contrastive Language-Image Pretraining: Prioritizing Data Quality over Quantity
di: Joshi, Siddharth, et al.
Pubblicazione: (2024)

Predicting Plasticity in Deep Continual Learning: A Theoretical Perspective
di: Wang, Jiuqi, et al.
Pubblicazione: (2026)

SpikCommander: A High-performance Spiking Transformer with Multi-view Learning for Efficient Speech Command Recognition
di: Wang, Jiaqi, et al.
Pubblicazione: (2025)

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

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

Conformal Prediction: A Theoretical Note and Benchmarking Transductive Node Classification in Graphs
di: Maneriker, Pranav, et al.
Pubblicazione: (2024)

Anonymous-by-Construction: An LLM-Driven Framework for Privacy-Preserving Text
di: Albanese, Federico, et al.
Pubblicazione: (2026)

Chordal Sparsity for Lipschitz Constant Estimation of Deep Neural Networks
di: Xue, Anton, et al.
Pubblicazione: (2022)

BPE: Behavioral Profiling Ensemble
di: Liu, Yanxin, et al.
Pubblicazione: (2026)