Cover Image

Paying Alignment Tax with Contrastive Learning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Korkmaz, Buse Sibel, Nair, Rahul, Daly, Elizabeth M., Chanona, Antonio del Rio
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Foundation Models at Work: Fine-Tuning for Fairness in Algorithmic Hiring
by: Korkmaz, Buse Sibel, et al.
Published: (2025)

Learning with Embedded Linear Equality Constraints via Variational Bayesian Inference
by: Marsh, Matthew, et al.
Published: (2026)

A Representation-Level Assessment of Bias Mitigation in Foundation Models
by: Nizhnichenkov, Svetoslav, et al.
Published: (2026)

Human-Algorithm Collaborative Bayesian Optimization for Engineering Systems
by: Savage, Tom, et al.
Published: (2024)

Humble AI in the real-world: the case of algorithmic hiring
by: Nair, Rahul, et al.
Published: (2025)

Ranking Large Language Models without Ground Truth
by: Dhurandhar, Amit, et al.
Published: (2024)

Mitigating the Alignment Tax of RLHF
by: Lin, Yong, et al.
Published: (2023)

SoDaDE: Solvent Data-Driven Embeddings with Small Transformer Models
by: Gibberd, Gabriel Kitso, et al.
Published: (2025)

Understanding and Diagnosing Deep Reinforcement Learning
by: Korkmaz, Ezgi
Published: (2024)

What Is the Alignment Tax?
by: Young, Robin
Published: (2026)

Safety Alignment as Continual Learning: Mitigating the Alignment Tax via Orthogonal Gradient Projection
by: Sun, Guanglong, et al.
Published: (2026)

A Survey Analyzing Generalization in Deep Reinforcement Learning
by: Korkmaz, Ezgi
Published: (2024)

bioLeak: Leakage-Aware Modeling and Diagnostics for Machine Learning in R
by: Korkmaz, Selçuk
Published: (2026)

Counteractive RL: Rethinking Core Principles for Efficient and Scalable Deep Reinforcement Learning
by: Korkmaz, Ezgi
Published: (2026)

Applying Multi-Fidelity Bayesian Optimization in Chemistry: Open Challenges and Major Considerations
by: Judge, Edmund, et al.
Published: (2024)

Prompt Smart, Pay Less: Cost-Aware APO for Real-World Applications
by: Choudhari, Jayesh, et al.
Published: (2025)

Machine Learning-Assisted Discovery of Flow Reactor Designs
by: Savage, Tom, et al.
Published: (2023)

Paying Less Generalization Tax: A Cross-Domain Generalization Study of RL Training for LLM Agents
by: Liu, Zhihan, et al.
Published: (2026)

Mitigating the Safety Alignment Tax with Null-Space Constrained Policy Optimization
by: Niu, Yifan, et al.
Published: (2025)

Reducing the Safety Tax in LLM Safety Alignment with On-Policy Self-Distillation
by: Fu, Yu, et al.
Published: (2026)

Holistic Bioprocess Development Across Scales Using Multi-Fidelity Batch Bayesian Optimization
by: Martens, Adrian, et al.
Published: (2025)

Black-box Uncertainty Quantification Method for LLM-as-a-Judge
by: Wagner, Nico, et al.
Published: (2024)

On the Alignment Between Supervised and Self-Supervised Contrastive Learning
by: Luthra, Achleshwar, et al.
Published: (2025)

Graph Contrastive Learning via Spectral Graph Alignment
by: Nguyen, Manh
Published: (2025)

Contrastive Diffusion Alignment: Learning Structured Latents for Controllable Generation
by: Sandilya, Ruchi, et al.
Published: (2025)

A Guide to Bayesian Optimization in Bioprocess Engineering
by: Siska, Maximilian, et al.
Published: (2025)

Online Merging Optimizers for Boosting Rewards and Mitigating Tax in Alignment
by: Lu, Keming, et al.
Published: (2024)

Reinforcement Learning with Semantic Rewards Enables Low-Resource Language Expansion without Alignment Tax
by: Su, Zeli, et al.
Published: (2026)

MILE: Model-based Intervention Learning
by: Korkmaz, Yigit, et al.
Published: (2025)

Multi-Alignment Contrastive Learning for Enzyme--Reaction Retrieval
by: Zhou, Gengmo, et al.
Published: (2025)

Capacity Provisioning Motivated Online Non-Convex Optimization Problem with Memory and Switching Cost
by: Vaze, Rahul, et al.
Published: (2024)

Reinforcement learning meets bioprocess control through behaviour cloning: Real-world deployment in an industrial photobioreactor
by: Gil, Juan D., et al.
Published: (2025)

Perfect Alignment May be Poisonous to Graph Contrastive Learning
by: Liu, Jingyu, et al.
Published: (2023)

Optimistic Exploration for Risk-Averse Constrained Reinforcement Learning
by: McCarthy, James, et al.
Published: (2025)

Shapelets-Enriched Selective Forecasting using Time Series Foundation Models
by: Tomar, Shivani, et al.
Published: (2026)

Cross-View Topology-Aware Graph Representation Learning
by: Korkmaz, Ahmet Sami, et al.
Published: (2025)

fastml: Guarded Resampling Workflows for Safer Automated Machine Learning in R
by: Korkmaz, Selcuk, et al.
Published: (2026)

Ultrasound Vision-Language Alignment via Contrastive Learning
by: Lyu, Zhuoyang, et al.
Published: (2026)

Cross-Modal Diffusion for Biomechanical Dynamical Systems Through Local Manifold Alignment
by: Dey, Sharmita, et al.
Published: (2025)

Robust Multimodal Learning via Entropy-Gated Contrastive Fusion
by: Chlon, Leon, et al.
Published: (2025)