:: Library Catalog

Cover Image

Saved in:

Bibliographic Details
Main Authors:	Jones, Erik, Tong, Meg, Mu, Jesse, Mahfoud, Mohammed, Leike, Jan, Grosse, Roger, Kaplan, Jared, Fithian, William, Perez, Ethan, Sharma, Mrinank
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	https://arxiv.org/abs/2502.16797
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Towards Safeguarding LLM Fine-tuning APIs against Cipher Attacks
by: Youstra, Jack, et al.
Published: (2025)

Rapid Response: Mitigating LLM Jailbreaks with a Few Examples
by: Peng, Alwin, et al.
Published: (2024)

Jailbreak Defense in a Narrow Domain: Limitations of Existing Methods and a New Transcript-Classifier Approach
by: Wang, Tony T., et al.
Published: (2024)

DELM: a Python toolkit for Data Extraction with Language Models
by: Fithian, Eric, et al.
Published: (2025)

A Flexible Defense Against the Winner's Curse
by: Zrnic, Tijana, et al.
Published: (2024)

Locally Simultaneous Inference
by: Zrnic, Tijana, et al.
Published: (2022)

Asymptotically Optimal Knockoff Statistics via the Masked Likelihood Ratio
by: Spector, Asher, et al.
Published: (2022)

Controlling the false discovery rate under a non-parametric graphical dependence model
by: Nguyen, Drew T., et al.
Published: (2025)

Reasoning Models Don't Always Say What They Think
by: Chen, Yanda, et al.
Published: (2025)

Best-of-N Jailbreaking
by: Hughes, John, et al.
Published: (2024)

Explaining Neural Scaling Laws
by: Bahri, Yasaman, et al.
Published: (2021)

Excess Description Length of Learning Generalizable Predictors
by: Donoway, Elizabeth, et al.
Published: (2026)

Eliciting Harmful Capabilities by Fine-Tuning On Safeguarded Outputs
by: Kaunismaa, Jackson, et al.
Published: (2026)

Improving knockoffs with conditional calibration
by: Luo, Yixiang, et al.
Published: (2022)

Estimating the False Discovery Rate of Variable Selection
by: Luo, Yixiang, et al.
Published: (2024)

Towards Understanding Sycophancy in Language Models
by: Sharma, Mrinank, et al.
Published: (2023)

Subjetividade, crise e educação ambiental
by: Miguel Mahfoud
Published: (2009)

Unidade da pessoa segundo Edith Stein: contribuições à educação para a nutrição
by: Miguel Mahfoud
Published: (2008)

Magnetic Effect on Thermocapillary Flow of Silicon Melt in an Annulus
by: Ali Bendjaghlouli, et al.
Published: (2024)

A frequentist local false discovery rate
by: Xiang, Daniel, et al.
Published: (2025)

PoisonBench: Assessing Large Language Model Vulnerability to Data Poisoning
by: Fu, Tingchen, et al.
Published: (2024)

Constitutional Classifiers++: Efficient Production-Grade Defenses against Universal Jailbreaks
by: Cunningham, Hoagy, et al.
Published: (2026)

Gaussian Rank Verification
by: Goldwasser, Jeremy, et al.
Published: (2025)

Unsupervised Elicitation of Language Models
by: Wen, Jiaxin, et al.
Published: (2025)

Who's in Charge? Disempowerment Patterns in Real-World LLM Usage
by: Sharma, Mrinank, et al.
Published: (2026)

Incorporating Unlabelled Data into Bayesian Neural Networks
by: Sharma, Mrinank, et al.
Published: (2023)

Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training
by: Hubinger, Evan, et al.
Published: (2024)

Domain-Specific Shorthand for Generation Based on Context-Free Grammar
by: Kanyuka, Andriy, et al.
Published: (2024)

Brachymetatarsia as an Early Clue to Turner Syndrome
by: Hounaida Mahfoud, et al.
Published: (2026)

KARMA: Karma-Aligned Reward Model Adaptation
by: Scott, Jared, et al.
Published: (2026)

Limit-Computable Grains of Truth for Arbitrary Computable Extensive-Form (Un)Known Games
by: Wyeth, Cole, et al.
Published: (2025)

Failures to Find Transferable Image Jailbreaks Between Vision-Language Models
by: Schaeffer, Rylan, et al.
Published: (2024)

Chain-of-Thought Hijacking
by: Zhao, Jianli, et al.
Published: (2025)

Mass-Producing Failures of Multimodal Systems with Language Models
by: Tong, Shengbang, et al.
Published: (2023)

Sabotage Evaluations for Frontier Models
by: Benton, Joe, et al.
Published: (2024)

Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming
by: Sharma, Mrinank, et al.
Published: (2025)

Smooth Models for Certain Fibered Partially Hyperbolic Systems
by: Doucette, Meg
Published: (2022)

On the convergence of the Born series for Coulomb potentials
by: Sussman, Ethan, et al.
Published: (2025)

Adaptive Deployment of Untrusted LLMs Reduces Distributed Threats
by: Wen, Jiaxin, et al.
Published: (2024)

Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models
by: Denison, Carson, et al.
Published: (2024)