Image de couverture de livre

Differentially Private Steering for Large Language Model Alignment

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Goel, Anmol, Hu, Yaxi, Gurevych, Iryna, Sanyal, Amartya
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Auditing Language Model Unlearning via Information Decomposition
par: Goel, Anmol, et autres
Publié: (2026)

Provable Privacy with Non-Private Pre-Processing
par: Hu, Yaxi, et autres
Publié: (2024)

How Quantization Shapes Bias in Large Language Models
par: Marcuzzi, Federico, et autres
Publié: (2025)

Factual Self-Awareness in Language Models: Representation, Robustness, and Scaling
par: Tamoyan, Hovhannes, et autres
Publié: (2025)

SpaRC and SpaRP: Spatial Reasoning Characterization and Path Generation for Understanding Spatial Reasoning Capability of Large Language Models
par: Rizvi, Md Imbesat Hassan, et autres
Publié: (2024)

Con Instruction: Universal Jailbreaking of Multimodal Large Language Models via Non-Textual Modalities
par: Geng, Jiahui, et autres
Publié: (2025)

Online Learning and Unlearning
par: Hu, Yaxi, et autres
Publié: (2025)

Stepwise Verification and Remediation of Student Reasoning Errors with Large Language Model Tutors
par: Daheim, Nico, et autres
Publié: (2024)

Socratic Reasoning Improves Positive Text Rewriting
par: Goel, Anmol, et autres
Publié: (2024)

Hierarchical Latent Structures in Data Generation Process Unify Mechanistic Phenomena across Scale
par: Rohweder, Jonas, et autres
Publié: (2026)

SPARE: Single-Pass Annotation with Reference-Guided Evaluation for Automatic Process Supervision and Reward Modelling
par: Rizvi, Md Imbesat Hassan, et autres
Publié: (2025)

LoRA and Privacy: When Random Projections Help (and When They Don't)
par: Hu, Yaxi, et autres
Publié: (2026)

Differentially Private Zeroth-Order Methods for Scalable Large Language Model Finetuning
par: Liu, Z, et autres
Publié: (2024)

An Iterative Algorithm for Differentially Private $k$-PCA with Adaptive Noise
par: Düngler, Johanna, et autres
Publié: (2025)

Differentially Private Next-Token Prediction of Large Language Models
par: Flemings, James, et autres
Publié: (2024)

Compositional Steering of Large Language Models with Steering Tokens
par: Radevski, Gorjan, et autres
Publié: (2026)

Differentially Private Tabular Data Synthesis using Large Language Models
par: Tran, Toan V., et autres
Publié: (2024)

Uncertainty-Aware Decoding with Minimum Bayes Risk
par: Daheim, Nico, et autres
Publié: (2025)

ABCD-LINK: Annotation Bootstrapping for Cross-Document Fine-Grained Links
par: Basch, Serwar, et autres
Publié: (2025)

Towards Automated Error Discovery: A Study in Conversational AI
par: Petrak, Dominic, et autres
Publié: (2025)

DP-Fusion: Token-Level Differentially Private Inference for Large Language Models
par: Thareja, Rushil, et autres
Publié: (2025)

On the Growth of Mistakes in Differentially Private Online Learning: A Lower Bound Perspective
par: Dmitriev, Daniil, et autres
Publié: (2024)

Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization
par: Cao, Yuanpu, et autres
Publié: (2024)

Model Merging by Uncertainty-Based Gradient Matching
par: Daheim, Nico, et autres
Publié: (2023)

ORCE: Order-Aware Alignment of Verbalized Confidence in Large Language Models
par: Li, Chen, et autres
Publié: (2026)

On The Truthfulness of 'Surprisingly Likely' Responses of Large Language Models
par: Goel, Naman
Publié: (2023)

LMO-DP: Optimizing the Randomization Mechanism for Differentially Private Fine-Tuning (Large) Language Models
par: Yang, Qin, et autres
Publié: (2024)

Steering Language Models with Weight Arithmetic
par: Fierro, Constanza, et autres
Publié: (2025)

Steering Language Models With Activation Engineering
par: Turner, Alexander Matt, et autres
Publié: (2023)

Alternate Preference Optimization for Unlearning Factual Knowledge in Large Language Models
par: Mekala, Anmol, et autres
Publié: (2024)

Attribute or Abstain: Large Language Models as Long Document Assistants
par: Buchmann, Jan, et autres
Publié: (2024)

Steering Large Language Models for Machine Translation Personalization
par: Scalena, Daniel, et autres
Publié: (2025)

DP-OPD: Differentially Private On-Policy Distillation for Language Models
par: Khadem, Fatemeh, et autres
Publié: (2026)

Vaccine: Perturbation-aware Alignment for Large Language Models against Harmful Fine-tuning Attack
par: Huang, Tiansheng, et autres
Publié: (2024)

SPS: Steering Probability Squeezing for Better Exploration in Reinforcement Learning for Large Language Models
par: Huo, Yifu, et autres
Publié: (2026)

COLD-Steer: Steering Large Language Models via In-Context One-step Learning Dynamics
par: Sharma, Kartik, et autres
Publié: (2026)

Robust Utility-Preserving Text Anonymization Based on Large Language Models
par: Yang, Tianyu, et autres
Publié: (2024)

CAST: Continuous and Differentiable Semi-Structured Sparsity-Aware Training for Large Language Models
par: Huang, Weiyu, et autres
Publié: (2025)

FedPDPO: Federated Personalized Direct Preference Optimization for Large Language Model Alignment
par: Zhu, Kewen, et autres
Publié: (2026)

Discovering Implicit Large Language Model Alignment Objectives
par: Chen, Edward, et autres
Publié: (2026)