Cover Image

Control Tax: The Price of Keeping AI in Check

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Terekhov, Mikhail, Liu, Zhen Ning David, Gulcehre, Caglar, Albanie, Samuel
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

In Search for Architectures and Loss Functions in Multi-Objective Reinforcement Learning
by: Terekhov, Mikhail, et al.
Published: (2024)

Adaptive Attacks on Trusted Monitors Subvert AI Control Protocols
by: Terekhov, Mikhail, et al.
Published: (2025)

The Role of Deep Learning Regularizations on Actors in Offline RL
by: Tarasov, Denis, et al.
Published: (2024)

One-Step is Enough: Sparse Autoencoders for Text-to-Image Diffusion Models
by: Surkov, Viacheslav, et al.
Published: (2024)

Simple Hierarchical Planning with Diffusion
by: Chen, Chang, et al.
Published: (2024)

PlanDQ: Hierarchical Plan Orchestration via D-Conductor and Q-Performer
by: Chen, Chang, et al.
Published: (2024)

Learning pure quantum states (almost) without regret
by: Lumbreras, Josep, et al.
Published: (2024)

Self-Recognition in Language Models
by: Davidson, Tim R., et al.
Published: (2024)

Regret-Optimized Portfolio Enhancement through Deep Reinforcement Learning and Future Looking Rewards
by: Karzanov, Daniil, et al.
Published: (2025)

Fleet of Agents: Coordinated Problem Solving with Large Language Models
by: Klein, Lars, et al.
Published: (2024)

Augmenting Attention with Exponentially Decaying Memory Improves Query-Aware KV Sparsity
by: Wei, Xiuying, et al.
Published: (2026)

BlockGen: Flexible Blockwise Sequence Modeling with Hybrid Samplers
by: Deschenaux, Justin, et al.
Published: (2026)

RAT+: Train Dense, Infer Sparse -- Recurrence Augmented Attention for Dilated Inference
by: Wei, Xiuying, et al.
Published: (2026)

Promises, Outlooks and Challenges of Diffusion Language Modeling
by: Deschenaux, Justin, et al.
Published: (2024)

From Markov to Laplace: How Mamba In-Context Learns Markov Chains
by: Bondaschi, Marco, et al.
Published: (2025)

Beyond Autoregression: Fast LLMs via Self-Distillation Through Time
by: Deschenaux, Justin, et al.
Published: (2024)

Keeping Medical AI Healthy and Trustworthy: A Review of Detection and Correction Methods for System Degradation
by: Guan, Hao, et al.
Published: (2025)

The Impact of Post-training on Data Contamination
by: Kocyigit, Muhammed Yusuf, et al.
Published: (2026)

Contextual Bandit Optimization with Pre-Trained Neural Networks
by: Terekhov, Mikhail
Published: (2025)

Integrating Attention-Enhanced LSTM and Particle Swarm Optimization for Dynamic Pricing and Replenishment Strategies in Fresh Food Supermarkets
by: Liu, Xianchen, et al.
Published: (2025)

Sanity Checks for Explanation Uncertainty
by: Valdenegro-Toro, Matias, et al.
Published: (2024)

Keep Rehearsing and Refining: Lifelong Learning Vehicle Routing under Continually Drifting Tasks
by: Pei, Jiyuan, et al.
Published: (2026)

Partition Generative Modeling: Masked Modeling Without Masks
by: Deschenaux, Justin, et al.
Published: (2025)

Quantile Reward Policy Optimization: Alignment with Pointwise Regression and Exact Partition Functions
by: Matrenok, Simon, et al.
Published: (2025)

Taxon: Hierarchical Tax Code Prediction with Semantically Aligned LLM Expert Guidance
by: Li, Jihang, et al.
Published: (2026)

Active Learning for Continual Learning: Keeping the Past Alive in the Present
by: Park, Jaehyun, et al.
Published: (2025)

Checking extracted rules in Neural Networks
by: Wurm, Adrian
Published: (2025)

Sanity Checks for Agentic Data Science
by: Rewolinski, Zachary T., et al.
Published: (2026)

seeBias: A Comprehensive Tool for Assessing and Visualizing AI Fairness
by: Ning, Yilin, et al.
Published: (2025)

Keep Everyone Happy: Online Fair Division of Numerous Items with Few Copies
by: Verma, Arun, et al.
Published: (2024)

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

Training with Confidence: Catching Silent Errors in Deep Learning Training with Automated Proactive Checks
by: Jiang, Yuxuan, et al.
Published: (2025)

The Alignment Tax: Response Homogenization in Aligned LLMs and Its Implications for Uncertainty Estimation
by: Liu, Mingyi
Published: (2026)

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

Regression Models Meet Foundation Models: A Hybrid-AI Approach to Practical Electricity Price Forecasting
by: Qiu, Yunzhong, et al.
Published: (2026)

Embedding Knowledge Graphs in Degenerate Clifford Algebras
by: Teyou, Louis Mozart Kamdem, et al.
Published: (2024)

Embedding Knowledge Graph in Function Spaces
by: Teyou, Louis Mozart Kamdem, et al.
Published: (2024)

The Diffusion Duality, Chapter II: $Ψ$-Samplers
by: Deschenaux, Justin, et al.
Published: (2026)

TaxDistill: Improving Metagenomic Taxonomic Annotation via Distilled Genomic Foundation Models
by: Ye, Rongye, et al.
Published: (2026)

When to Trust the Cheap Check: Weak and Strong Verification for Reasoning
by: Kiyani, Shayan, et al.
Published: (2026)