Imagen de Portada

Auditing language models for hidden objectives

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Marks, Samuel, Treutlein, Johannes, Bricken, Trenton, Lindsey, Jack, Marcus, Jonathan, Mishra-Sharma, Siddharth, Ziegler, Daniel, Ameisen, Emmanuel, Batson, Joshua, Belonax, Tim, Bowman, Samuel R., Carter, Shan, Chen, Brian, Cunningham, Hoagy, Denison, Carson, Dietz, Florian, Golechha, Satvik, Khan, Akbir, Kirchner, Jan, Leike, Jan, Meek, Austin, Nishimura-Gasparian, Kei, Ong, Euan, Olah, Christopher, Pearce, Adam, Roger, Fabien, Salle, Jeanne, Shih, Andy, Tong, Meg, Thomas, Drake, Rivoire, Kelley, Jermyn, Adam, MacDiarmid, Monte, Henighan, Tom, Hubinger, Evan
Formato:	Preprint
Publicado:	2025
Materias:	Artificial Intelligence Computation and Language Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet
por: Templeton, Adly, et al.
Publicado: (2026)

Alignment faking in large language models
por: Greenblatt, Ryan, et al.
Publicado: (2024)

Progress Measures for Grokking on Real-world Tasks
por: Golechha, Satvik
Publicado: (2024)

When Models Manipulate Manifolds: The Geometry of a Counting Task
por: Gurnee, Wes, et al.
Publicado: (2026)

Cross-Architecture Model Diffing with Crosscoders: Unsupervised Discovery of Differences Between LLMs
por: Jiralerspong, Thomas, et al.
Publicado: (2026)

Natural Emergent Misalignment from Reward Hacking in Production RL
por: MacDiarmid, Monte, et al.
Publicado: (2025)

Challenges in Mechanistically Interpreting Model Representations
por: Golechha, Satvik, et al.
Publicado: (2024)

Among Us: A Sandbox for Measuring and Detecting Agentic Deception
por: Golechha, Satvik, et al.
Publicado: (2025)

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

Training Neural Networks for Modularity aids Interpretability
por: Golechha, Satvik, et al.
Publicado: (2024)

Emotion Concepts and their Function in a Large Language Model
por: Sofroniew, Nicholas, et al.
Publicado: (2026)

Scottish meat consumption survey (Feb–Jul 2023): attitudes, COM-B measures, and perceived effectiveness of meat-reduction policies (Best-Worst Scaling)
por: McBey, David, et al.
Publicado: (2026)

NICE: To Optimize In-Context Examples or Not?
por: Srivastava, Pragya, et al.
Publicado: (2024)

Circumbinary discs for stellar population models
por: Izzard, Robert G., et al.
Publicado: (2024)

A Post‐Pandemic Bail System: Lessons Learned From Supervising Accused During Covid‐19
por: Laura MacDiarmid, et al.
Publicado: (2025)

Building Better Deception Probes Using Targeted Instruction Pairs
por: Natarajan, Vikram, et al.
Publicado: (2026)

ABBEL: LLM Agents Acting through Belief Bottlenecks Expressed in Language
por: Lidayan, Aly, et al.
Publicado: (2025)

Studying Cross-cluster Modularity in Neural Networks
por: Golechha, Satvik, et al.
Publicado: (2025)

Das Berlin Max Webers
por: Aldenhoff-Hübinger, Rita, et al.
Publicado: (2026)

Polysemanticity and Capacity in Neural Networks
por: Scherlis, Adam, et al.
Publicado: (2022)

Who's the Evil Twin? Differential Auditing for Undesired Behavior
por: Balappanawar, Ishwar, et al.
Publicado: (2025)

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

Latent Planning Emerges with Scale
por: Hanna, Michael, et al.
Publicado: (2026)

Descriptions of new fishes from Panama
por: Meek, Seth E., et al.
Publicado: (1912)

New species of fishes from Panama
por: Meek, Seth E., et al.
Publicado: (1913)

A is for Absorption: Studying Feature Splitting and Absorption in Sparse Autoencoders
por: Chanin, David, et al.
Publicado: (2024)

Europa desde 1918 hasta hoy / Mario Rivoire ; Traducción al español por Carlos Gerhard
por: Rivoire, Mario
Publicado: (1918)

Continuous data assimilation for the Richards equation of unsaturated flow: A computational study
por: Amanda Rowley, et al.
Publicado: (2026)

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

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

Government Publications in Kansas Public Libraries.
por: Batson, Donald
Publicado: (1975)

Steering Language Models With Activation Engineering
por: Turner, Alexander Matt, et al.
Publicado: (2023)

CataractBot: An LLM-Powered Expert-in-the-Loop Chatbot for Cataract Patients
por: Ramjee, Pragnya, et al.
Publicado: (2024)

Descriptions of new Fishes from Panama
por: Meek, Seth E. (Seth Eugene), et al.
Publicado: (1912)

School of Reward Hacks: Hacking harmless tasks generalizes to misaligned behavior in LLMs
por: Taylor, Mia, et al.
Publicado: (2025)

Pendant appearances and components in random graphs from structured classes
por: McDiarmid, Colin
Publicado: (2021)

The Savage Worlds of Henry Drummond (1851–1897): Science, Racism and Religion in the Work of a Popular Evolutionist
por: Diarmid A. Finnegan
Publicado: (2025)

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

State Government Publications: Selection, Acquisition, and Reference Service.
por: Batson, Donald W.
Publicado: (1990)

AD genes and microglia phenotypes: does microglia phenotypic heterogeneity matter?
por: Marta Olah
Publicado: (2024)