Image de couverture de livre

BarrierSteer: LLM Safety via Learning Barrier Steering

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Tran, Thanh Q., Verma, Arun, Wong, Kiwan, Low, Bryan Kian Hsiang, Rus, Daniela, Xiao, Wei
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

ActiveDPO: Active Direct Preference Optimization for Sample-Efficient Alignment
par: Lin, Xiaoqiang, et autres
Publié: (2025)

Keep Everyone Happy: Online Fair Division of Numerous Items with Few Copies
par: Verma, Arun, et autres
Publié: (2024)

COBRA: Contextual Bandit Algorithm for Ensuring Truthful Strategic Agents
par: Verma, Arun, et autres
Publié: (2025)

Data value estimation on private gradients
par: Zhou, Zijian, et autres
Publié: (2024)

MineDraft: A Framework for Batch Parallel Speculative Decoding
par: Tang, Zhenwei, et autres
Publié: (2026)

Neural Dueling Bandits: Preference-Based Optimization with Human Feedback
par: Verma, Arun, et autres
Publié: (2024)

TETRIS: Optimal Draft Token Selection for Batch Speculative Decoding
par: Wu, Zhaoxuan, et autres
Publié: (2025)

DETAIL: Task DEmonsTration Attribution for Interpretable In-context Learning
par: Zhou, Zijian, et autres
Publié: (2024)

Active Human Feedback Collection via Neural Contextual Dueling Bandits
par: Verma, Arun, et autres
Publié: (2025)

Prompt Optimization with Human Feedback
par: Lin, Xiaoqiang, et autres
Publié: (2024)

Dependency Structure Search Bayesian Optimization for Decision Making Models
par: Rajpal, Mohit, et autres
Publié: (2023)

DeRDaVa: Deletion-Robust Data Valuation for Machine Learning
par: Tian, Xiao, et autres
Publié: (2023)

MeMo: Memory as a Model
par: Quek, Ryan Wei Heng, et autres
Publié: (2026)

BoLT: A Benchmark to Democratize Black-box Optimization Research for Expensive LLM Tasks
par: Chew, Ruth Wan Theng, et autres
Publié: (2026)

PoSafeNet: Safe Learning with Poset-Structured Neural Nets
par: Wong, Kiwan, et autres
Publié: (2026)

The Rogue Scalpel: Activation Steering Compromises LLM Safety
par: Korznikov, Anton, et autres
Publié: (2025)

Graph-Regularized Sparse Autoencoders for LLM Safety Steering
par: Yeon, Jehyeok, et autres
Publié: (2025)

INO-SGD: Addressing Utility Imbalance under Individualized Differential Privacy
par: Tian, Xiao, et autres
Publié: (2026)

SteeringSafety: A Systematic Safety Evaluation Framework of Representation Steering in LLMs
par: Siu, Vincent, et autres
Publié: (2025)

DUET: Optimizing Training Data Mixtures via Feedback from Unseen Evaluation Tasks
par: Chen, Zhiliang, et autres
Publié: (2025)

Steering LLMs for Formal Theorem Proving
par: Kirtania, Shashank, et autres
Publié: (2025)

Incentivizing Truthfulness and Collaborative Fairness in Bayesian Learning
par: Sim, Rachael Hwee Ling, et autres
Publié: (2026)

Steer Like the LLM: Activation Steering that Mimics Prompting
par: Heyman, Geert, et autres
Publié: (2026)

Paid with Models: Optimal Contract Design for Collaborative Machine Learning
par: Wang, Bingchen, et autres
Publié: (2024)

Group-robust Sample Reweighting for Subpopulation Shifts via Influence Functions
par: Qiao, Rui, et autres
Publié: (2025)

Steered LLM Activations are Non-Surjective
par: Mishra, Aayush, et autres
Publié: (2026)

Preemptive Detection and Steering of LLM Misalignment via Latent Reachability
par: Karnik, Sathwik, et autres
Publié: (2025)

Helpful or Harmful Data? Fine-tuning-free Shapley Attribution for Explaining Language Model Predictions
par: Wang, Jingtan, et autres
Publié: (2024)

Global Evolutionary Steering: Refining Activation Steering Control via Cross-Layer Consistency
par: Jiang, Xinyan, et autres
Publié: (2026)

Fine-tuning Language Models with Generative Adversarial Reward Modelling
par: Yu, Zhang Ze, et autres
Publié: (2023)

REFRAG: Rethinking RAG based Decoding
par: Lin, Xiaoqiang, et autres
Publié: (2025)

Ferret: Federated Full-Parameter Tuning at Scale for Large Language Models
par: Shu, Yao, et autres
Publié: (2024)

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

Concept Heterogeneity-aware Representation Steering
par: Abdullaev, Laziz U., et autres
Publié: (2026)

Kernel-Based Learning of Safety Barriers
par: Schön, Oliver, et autres
Publié: (2026)

To Steer or Not to Steer? Mechanistic Error Reduction with Abstention for Language Models
par: Hedström, Anna, et autres
Publié: (2025)

MidSteer: Optimal Affine Framework for Steering Generative Models
par: Gaintseva, Tatiana, et autres
Publié: (2026)

Steer LLM Latents for Hallucination Detection
par: Park, Seongheon, et autres
Publié: (2025)

AlphaSteer: Learning Refusal Steering with Principled Null-Space Constraint
par: Sheng, Leheng, et autres
Publié: (2025)

Is Data Shapley Not Better than Random in Data Selection? Ask NASH
par: Tian, Xiao, et autres
Publié: (2026)