Imagen de Portada

Base Models Know How to Reason, Thinking Models Learn When

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Venhoff, Constantin, Arcuschin, Iván, Torr, Philip, Conmy, Arthur, Nanda, Neel
Formato:	Preprint
Publicado:	2025
Materias:	Artificial Intelligence Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Understanding Reasoning in Thinking Language Models via Steering Vectors
por: Venhoff, Constantin, et al.
Publicado: (2025)

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

Automatically Finding Reward Model Biases
por: Wang, Atticus, et al.
Publicado: (2026)

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

Reasoning-Finetuning Repurposes Latent Representations in Base Models
por: Ward, Jake, et al.
Publicado: (2025)

How Visual Representations Map to Language Feature Space in Multimodal LLMs
por: Venhoff, Constantin, et al.
Publicado: (2025)

Too Late to Recall: Explaining the Two-Hop Problem in Multimodal Knowledge Retrieval
por: Venhoff, Constantin, et al.
Publicado: (2025)

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

Improving Dictionary Learning with Gated Sparse Autoencoders
por: Rajamanoharan, Senthooran, et al.
Publicado: (2024)

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

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

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

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

AdaptThink: Reasoning Models Can Learn When to Think
por: Zhang, Jiajie, et al.
Publicado: (2025)

Inference-Time Toxicity Mitigation in Protein Language Models
por: Burda, Manuel Fernández, et al.
Publicado: (2026)

When Models Know When They Do Not Know: Calibration, Cascading, and Cleaning
por: Hao, Chenjie, et al.
Publicado: (2026)

Epistemic Deep Learning: Enabling Machine Learning Models to Know When They Do Not Know
por: Manchingal, Shireen Kudukkil
Publicado: (2025)

Subliminal Learning Is Steering Vector Distillation
por: Blank, Camila, et al.
Publicado: (2026)

Model Organisms for Emergent Misalignment
por: Turner, Edward, et al.
Publicado: (2025)

Applying sparse autoencoders to unlearn knowledge in language models
por: Farrell, Eoin, et al.
Publicado: (2024)

Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2
por: Lieberum, Tom, et al.
Publicado: (2024)

Learning Multi-Level Features with Matryoshka Sparse Autoencoders
por: Bussmann, Bart, et al.
Publicado: (2025)

An MRP Formulation for Supervised Learning: Generalized Temporal Difference Learning Models
por: Pan, Yangchen, et al.
Publicado: (2024)

BatchTopK Sparse Autoencoders
por: Bussmann, Bart, et al.
Publicado: (2024)

Improving Steering Vectors by Targeting Sparse Autoencoder Features
por: Chalnev, Sviatoslav, et al.
Publicado: (2024)

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

When Models Know More Than They Say: Probing Analogical Reasoning in LLMs
por: McGovern, Hope, et al.
Publicado: (2026)

Biases in the Blind Spot: Detecting What LLMs Fail to Mention
por: Arcuschin, Iván, et al.
Publicado: (2026)

Conformal Alignment: Knowing When to Trust Foundation Models with Guarantees
por: Gui, Yu, et al.
Publicado: (2024)

How do LLMs Compute Verbal Confidence
por: Kumaran, Dharshan, et al.
Publicado: (2026)

Simple LLM Baselines are Competitive for Model Diffing
por: Kempf, Elias, et al.
Publicado: (2026)

Convergent Linear Representations of Emergent Misalignment
por: Soligo, Anna, et al.
Publicado: (2025)

L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning
por: Aggarwal, Pranjal, et al.
Publicado: (2025)

Do Large Language Models Know How Much They Know?
por: Prato, Gabriele, et al.
Publicado: (2025)

Know Where You're Uncertain When Planning with Multimodal Foundation Models: A Formal Framework
por: Bhatt, Neel P., et al.
Publicado: (2024)

SAGE: Scalable Ground Truth Evaluations for Large Sparse Autoencoders
por: Venhoff, Constantin, et al.
Publicado: (2024)

Towards Interpretable Sequence Continuation: Analyzing Shared Circuits in Large Language Models
por: Lan, Michael, et al.
Publicado: (2023)

What Large Language Models Know and What People Think They Know
por: Steyvers, Mark, et al.
Publicado: (2024)

NanoKnow: How to Know What Your Language Model Knows
por: Gu, Lingwei, et al.
Publicado: (2026)

Are Sparse Autoencoders Useful? A Case Study in Sparse Probing
por: Kantamneni, Subhash, et al.
Publicado: (2025)