Cover Image

Classifier-free guidance in LLMs Safety

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	Smirnov, Roman
Format:	Preprint
Published:	2024
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Hypernym Bias: Unraveling Deep Classifier Training Dynamics through the Lens of Class Hierarchy
by: Malashin, Roman, et al.
Published: (2025)

Understanding and Preserving Safety in Fine-Tuned LLMs
by: Zhang, Jiawen, et al.
Published: (2026)

Breaking the Safety-Capability Tradeoff: Reinforcement Learning with Verifiable Rewards Maintains Safety Guardrails in LLMs
by: Cho, Dongkyu Derek, et al.
Published: (2025)

Debiasing Text Safety Classifiers through a Fairness-Aware Ensemble
by: Sturman, Olivia, et al.
Published: (2024)

LongSafety: Enhance Safety for Long-Context LLMs
by: Huang, Mianqiu, et al.
Published: (2024)

EasyQuant: An Efficient Data-free Quantization Algorithm for LLMs
by: Tang, Hanlin, et al.
Published: (2024)

Amplifying, Not Learning: Fine-Tuned AI Text Detectors Amplify a Pretrained Direction
by: Smirnov, Alexander
Published: (2026)

Beyond Retention: Orchestrating Structural Safety and Plasticity in Continual Learning for LLMs
by: Meng, Fei
Published: (2026)

Diffusion Models without Classifier-free Guidance
by: Tang, Zhicong, et al.
Published: (2025)

Understanding and Mitigating Overrefusal in LLMs from an Unveiling Perspective of Safety Decision Boundary
by: Pan, Licheng, et al.
Published: (2025)

Safety at One Shot: Patching Fine-Tuned LLMs with A Single Instance
by: Zhang, Jiawen, et al.
Published: (2026)

One-shot Optimized Steering Vectors Mediate Safety-relevant Behaviors in LLMs
by: Dunefsky, Jacob, et al.
Published: (2025)

Any-Depth Alignment: Unlocking Innate Safety Alignment of LLMs to Any-Depth
by: Zhang, Jiawei, et al.
Published: (2025)

Classifying Overlapping Gaussian Mixtures in High Dimensions: From Optimal Classifiers to Neural Nets
by: Cohen, Khen, et al.
Published: (2024)

On Continuity of Robust and Accurate Classifiers
by: Barati, Ramin, et al.
Published: (2023)

SteeringSafety: A Systematic Safety Evaluation Framework of Representation Steering in LLMs
by: Siu, Vincent, et al.
Published: (2025)

Efficient Safety Retrofitting Against Jailbreaking for LLMs
by: Garcia-Gasulla, Dario, et al.
Published: (2025)

Efficiency vs. Alignment: Investigating Safety and Fairness Risks in Parameter-Efficient Fine-Tuning of LLMs
by: Taraghi, Mina, et al.
Published: (2025)

Safe Pruning LoRA: Robust Distance-Guided Pruning for Safety Alignment in Adaptation of LLMs
by: Ao, Shuang, et al.
Published: (2025)

Confidence Calibration of Classifiers with Many Classes
by: LeCoz, Adrien, et al.
Published: (2024)

Interpretable and Fair Mechanisms for Abstaining Classifiers
by: Lenders, Daphne, et al.
Published: (2025)

Fixed Random Classifier Rearrangement for Continual Learning
by: Huang, Shengyang, et al.
Published: (2024)

Generating Universal Adversarial Perturbations for Quantum Classifiers
by: Anil, Gautham, et al.
Published: (2024)

Deep Classifier Mimicry without Data Access
by: Braun, Steven, et al.
Published: (2023)

Fairness of Classifiers in the Presence of Constraints between Features
by: Cooper, Martin C., et al.
Published: (2026)

Simple and Effective Specialized Representations for Fair Classifiers
by: Sinigaglia, Alberto, et al.
Published: (2025)

Understanding Prediction Discrepancies in Machine Learning Classifiers
by: Renard, Xavier, et al.
Published: (2021)

Bayesian Inference for Correlated Human Experts and Classifiers
by: Kelly, Markelle, et al.
Published: (2025)

Better as Generators Than Classifiers: Leveraging LLMs and Synthetic Data for Low-Resource Multilingual Classification
by: Pecher, Branislav, et al.
Published: (2026)

Exploiting Synergistic Cognitive Biases to Bypass Safety in LLMs
by: Yang, Xikang, et al.
Published: (2025)

Evaluating Multimodal LLMs for Inpatient Diagnosis: Real-World Performance, Safety, and Cost Across Ten Frontier Models
by: Bassett, Bruce A., et al.
Published: (2026)

Improving Continual Learning Performance and Efficiency with Auxiliary Classifiers
by: Szatkowski, Filip, et al.
Published: (2024)

Demystifying the Optimal Fair Classifier in Multi-Class Classification
by: Zhang, Li, et al.
Published: (2026)

On the Usefulness of the Fit-on-the-Test View on Evaluating Calibration of Classifiers
by: Kängsepp, Markus, et al.
Published: (2022)

Efficient Controllable Diffusion via Optimal Classifier Guidance
by: Oertell, Owen, et al.
Published: (2025)

A Practical Approach to using Supervised Machine Learning Models to Classify Aviation Safety Occurrences
by: Siow, Bryan Y.
Published: (2025)

Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks
by: Andriushchenko, Maksym, et al.
Published: (2024)

Closed-Form Interpretation of Neural Network Classifiers with Symbolic Gradients
by: Wetzel, Sebastian Johann
Published: (2024)

XNB: Explainable Class-Specific NaIve-Bayes Classifier
by: Aguilar-Ruiz, Jesus S., et al.
Published: (2024)

Distribution-Based Feature Attribution for Explaining the Predictions of Any Classifier
by: Li, Xinpeng, et al.
Published: (2025)