Cover Image

Censored LLMs as a Natural Testbed for Secret Knowledge Elicitation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Casademunt, Helena, Cywiński, Bartosz, Tran, Khoi, Jakkli, Arya, Marks, Samuel, Nanda, Neel
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Steering Out-of-Distribution Generalization with Concept Ablation Fine-Tuning
by: Casademunt, Helena, et al.
Published: (2025)

Eliciting Secret Knowledge from Language Models
by: Cywiński, Bartosz, et al.
Published: (2025)

How Well Do Models Follow Their Constitutions?
by: Jakkli, Arya, et al.
Published: (2026)

Explorations of Self-Repair in Language Models
by: Rushing, Cody, et al.
Published: (2024)

Towards Best Practices of Activation Patching in Language Models: Metrics and Methods
by: Zhang, Fred, et al.
Published: (2023)

Do I Know This Entity? Knowledge Awareness and Hallucinations in Language Models
by: Ferrando, Javier, et al.
Published: (2024)

What's the plan? Metrics for implicit planning in LLMs and their application to rhyme generation and question answering
by: Maar, Jim, et al.
Published: (2026)

SUPERNOVA: Eliciting General Reasoning in LLMs with Reinforcement Learning on Natural Instructions
by: Suvarna, Ashima, et al.
Published: (2026)

Thought Branches: Interpreting LLM Reasoning Requires Resampling
by: Macar, Uzay, et al.
Published: (2025)

Thought Anchors: Which LLM Reasoning Steps Matter?
by: Bogdan, Paul C., et al.
Published: (2025)

Scaling sparse feature circuit finding for in-context learning
by: Kharlapenko, Dmitrii, et al.
Published: (2025)

Overcoming Sparsity Artifacts in Crosscoders to Interpret Chat-Tuning
by: Minder, Julian, et al.
Published: (2025)

Robustly Improving LLM Fairness in Realistic Settings via Interpretability
by: Karvonen, Adam, et al.
Published: (2025)

Evaluating Sparse Autoencoders on Targeted Concept Erasure Tasks
by: Karvonen, Adam, et al.
Published: (2024)

Narrow Finetuning Leaves Clearly Readable Traces in Activation Differences
by: Minder, Julian, et al.
Published: (2025)

SAeUron: Interpretable Concept Unlearning in Diffusion Models with Sparse Autoencoders
by: Cywiński, Bartosz, et al.
Published: (2025)

Adaptive Elicitation of Latent Information Using Natural Language
by: Wang, Jimmy, et al.
Published: (2025)

Steering Evaluation-Aware Language Models to Act Like They Are Deployed
by: Hua, Tim Tian, et al.
Published: (2025)

Eliciting Latent Knowledge from Quirky Language Models
by: Mallen, Alex, et al.
Published: (2023)

Towards eliciting latent knowledge from LLMs with mechanistic interpretability
by: Cywiński, Bartosz, et al.
Published: (2025)

Layerwise Recall and the Geometry of Interwoven Knowledge in LLMs
by: Lei, Ge, et al.
Published: (2025)

Chain-of-Thought Reasoning In The Wild Is Not Always Faithful
by: Arcuschin, Iván, et al.
Published: (2025)

Real-Time Detection of Hallucinated Entities in Long-Form Generation
by: Obeso, Oscar, et al.
Published: (2025)

The Impact of Inference Acceleration on Bias of LLMs
by: Kirsten, Elisabeth, et al.
Published: (2024)

Connecting the Dots: LLMs can Infer and Verbalize Latent Structure from Disparate Training Data
by: Treutlein, Johannes, et al.
Published: (2024)

Confidence Regulation Neurons in Language Models
by: Stolfo, Alessandro, et al.
Published: (2024)

Building Production-Ready Probes For Gemini
by: Kramár, János, et al.
Published: (2026)

Refusal in Language Models Is Mediated by a Single Direction
by: Arditi, Andy, et al.
Published: (2024)

Steer2Adapt: Dynamically Composing Steering Vectors Elicits Efficient Adaptation of LLMs
by: Han, Pengrui, et al.
Published: (2026)

Speak Easy: Eliciting Harmful Jailbreaks from LLMs with Simple Interactions
by: Chan, Yik Siu, et al.
Published: (2025)

Evaluating Prompt Engineering Techniques for Accuracy and Confidence Elicitation in Medical LLMs
by: Naderi, Nariman, et al.
Published: (2025)

Generalization of RLVR Using Causal Reasoning as a Testbed
by: Lu, Brian, et al.
Published: (2025)

Universal Neurons in GPT2 Language Models
by: Gurnee, Wes, et al.
Published: (2024)

TracrBench: Generating Interpretability Testbeds with Large Language Models
by: Thurnherr, Hannes, et al.
Published: (2024)

Data Cartography for Detecting Memorization Hotspots and Guiding Data Interventions in Generative Models
by: Patel, Laksh, et al.
Published: (2025)

Activation Oracles: Training and Evaluating LLMs as General-Purpose Activation Explainers
by: Karvonen, Adam, et al.
Published: (2025)

Certifying Knowledge Comprehension in LLMs
by: Chaudhary, Isha, et al.
Published: (2024)

Countdown-Code: A Testbed for Studying The Emergence and Generalization of Reward Hacking in RLVR
by: Khalifa, Muhammad, et al.
Published: (2026)

Eliciting Language Model Behaviors with Investigator Agents
by: Li, Xiang Lisa, et al.
Published: (2025)

Online Rubrics Elicitation from Pairwise Comparisons
by: Rezaei, MohammadHossein, et al.
Published: (2025)