Copertina

Detoxifying LLMs via Representation Erasure-Based Preference Optimization

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Sepahvand, Nazanin Mohammadi, Triantafillou, Eleni, Larochelle, Hugo, Precup, Doina, Roy, Daniel M., Dziugaite, Gintare Karolina
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Data Selection for Transfer Unlearning
di: Sepahvand, Nazanin Mohammadi, et al.
Pubblicazione: (2024)

Leveraging Per-Instance Privacy for Machine Unlearning
di: Sepahvand, Nazanin Mohammadi, et al.
Pubblicazione: (2025)

Improved Localized Machine Unlearning Through the Lens of Memorization
di: Torkzadehmahani, Reihaneh, et al.
Pubblicazione: (2024)

The Non-Local Model Merging Problem: Permutation Symmetries and Variance Collapse
di: Sharma, Ekansh, et al.
Pubblicazione: (2024)

Information Complexity of Stochastic Convex Optimization: Applications to Generalization and Memorization
di: Attias, Idan, et al.
Pubblicazione: (2024)

From Dormant to Deleted: Tamper-Resistant Unlearning Through Weight-Space Regularization
di: Siddiqui, Shoaib Ahmed, et al.
Pubblicazione: (2025)

Unlearning in- vs. out-of-distribution data in LLMs under gradient-based method
di: Baluta, Teodora, et al.
Pubblicazione: (2024)

On Traceability in $\ell_p$ Stochastic Convex Optimization
di: Voitovych, Sasha, et al.
Pubblicazione: (2025)

Mixtures of Experts Unlock Parameter Scaling for Deep RL
di: Obando-Ceron, Johan, et al.
Pubblicazione: (2024)

Simultaneous linear connectivity of neural networks modulo permutation
di: Sharma, Ekansh, et al.
Pubblicazione: (2024)

Less is More: Undertraining Experts Improves Model Upcycling
di: Horoi, Stefan, et al.
Pubblicazione: (2025)

Mechanistic Unlearning: Robust Knowledge Unlearning and Editing via Mechanistic Localization
di: Guo, Phillip, et al.
Pubblicazione: (2024)

Capturing Individual Human Preferences with Reward Features
di: Barreto, André, et al.
Pubblicazione: (2025)

Identifying Spurious Biases Early in Training through the Lens of Simplicity Bias
di: Yang, Yu, et al.
Pubblicazione: (2023)

Conditions on Preference Relations that Guarantee the Existence of Optimal Policies
di: Carr, Jonathan Colaço, et al.
Pubblicazione: (2023)

Leveraging Function Space Aggregation for Federated Learning at Scale
di: Dhawan, Nikita, et al.
Pubblicazione: (2023)

Dataset Difficulty and the Role of Inductive Bias
di: Kwok, Devin, et al.
Pubblicazione: (2024)

A Look at Value-Based Decision-Time vs. Background Planning Methods Across Different Settings
di: Alver, Safa, et al.
Pubblicazione: (2022)

Reinforcement Learning with Pairwise Preferences in Long-Term Decision Problems
di: Carr, Jonathan Colaço, et al.
Pubblicazione: (2026)

Soup to go: mitigating forgetting during continual learning with model averaging
di: Kleiman, Anat, et al.
Pubblicazione: (2025)

Are we making progress in unlearning? Findings from the first NeurIPS unlearning competition
di: Triantafillou, Eleni, et al.
Pubblicazione: (2024)

Diversity-Enriched Option-Critic
di: Kamat, Anand, et al.
Pubblicazione: (2020)

Functional Acceleration for Policy Mirror Descent
di: Chelu, Veronica, et al.
Pubblicazione: (2024)

Evaluating Interventional Reasoning Capabilities of Large Language Models
di: Kasetty, Tejas, et al.
Pubblicazione: (2024)

Incorporating Spatial Information into Goal-Conditioned Hierarchical Reinforcement Learning via Graph Representations
di: Zhang, Shuyuan, et al.
Pubblicazione: (2025)

Continual Learning in Vision-Language Models via Aligned Model Merging
di: Sokar, Ghada, et al.
Pubblicazione: (2025)

Balancing Plasticity and Stability with Fast and Slow Successor Features
di: Chua, Raymond, et al.
Pubblicazione: (2026)

Partial Models for Building Adaptive Model-Based Reinforcement Learning Agents
di: Alver, Safa, et al.
Pubblicazione: (2024)

SSFL: Discovering Sparse Unified Subnetworks at Initialization for Efficient Federated Learning
di: Ohib, Riyasat, et al.
Pubblicazione: (2024)

On the Privacy of Selection Mechanisms with Gaussian Noise
di: Lebensold, Jonathan, et al.
Pubblicazione: (2024)

What makes unlearning hard and what to do about it
di: Zhao, Kairan, et al.
Pubblicazione: (2024)

The Journey Matters: Average Parameter Count over Pre-training Unifies Sparse and Dense Scaling Laws
di: Jin, Tian, et al.
Pubblicazione: (2025)

Torque-Aware Momentum
di: Malviya, Pranshu, et al.
Pubblicazione: (2024)

Sparse-Reg: Improving Sample Complexity in Offline Reinforcement Learning using Sparsity
di: Arnob, Samin Yeasar, et al.
Pubblicazione: (2025)

Adaptive Exploration for Data-Efficient General Value Function Evaluations
di: Jain, Arushi, et al.
Pubblicazione: (2024)

Relative Trajectory Balance is equivalent to Trust-PCL
di: Deleu, Tristan, et al.
Pubblicazione: (2025)

Capacity-Constrained Continual Learning
di: Wen, Zheng, et al.
Pubblicazione: (2025)

Fluid-Agent Reinforcement Learning
di: Sharma, Shishir, et al.
Pubblicazione: (2026)

Langevin Soft Actor-Critic: Efficient Exploration through Uncertainty-Driven Critic Learning
di: Ishfaq, Haque, et al.
Pubblicazione: (2025)

Offline Multitask Representation Learning for Reinforcement Learning
di: Ishfaq, Haque, et al.
Pubblicazione: (2024)