Cover Image

Internal states before wait modulate reasoning patterns

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Troitskii, Dmitrii, Pal, Koyena, Wendler, Chris, McDougall, Callum Stuart, Nanda, Neel
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

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)

Do explanations generalize across large reasoning models?
by: Pal, Koyena, et al.
Published: (2026)

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

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)

Emergent Misalignment is Easy, Narrow Misalignment is Hard
by: Soligo, Anna, et al.
Published: (2026)

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

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

Separating Tongue from Thought: Activation Patching Reveals Language-Agnostic Concept Representations in Transformers
by: Dumas, Clément, et al.
Published: (2024)

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)

Phi-4-reasoning Technical Report
by: Abdin, Marah, et al.
Published: (2025)

Transfer Learning from Foundational Optimization Embeddings to Unsupervised SAT Representations
by: Pal, Koyena, et al.
Published: (2026)

Discovering Forbidden Topics in Language Models
by: Rager, Can, et al.
Published: (2025)

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

Catching rationalization in the act: detecting motivated reasoning before and after CoT via activation probing
by: Mirtaheri, Parsa, et al.
Published: (2026)

Hey, wait a minute: on at-issue sensitivity in Language Models
by: Kim, Sanghee J., et al.
Published: (2025)

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

Your thoughts tell who you are: Characterize the reasoning patterns of LRMs
by: Chen, Yida, et al.
Published: (2025)

Steering Out-of-Distribution Generalization with Concept Ablation Fine-Tuning
by: Casademunt, Helena, 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)

Controllable Context Sensitivity and the Knob Behind It
by: Minder, Julian, et al.
Published: (2024)

Censored LLMs as a Natural Testbed for Secret Knowledge Elicitation
by: Casademunt, Helena, et al.
Published: (2026)

FOSSIL: Harnessing Feedback on Suboptimal Samples for Data-Efficient Generalisation with Imitation Learning for Embodied Vision-and-Language Tasks
by: McCallum, Sabrina, et al.
Published: (2025)

CoT-Self-Instruct: Building high-quality synthetic prompts for reasoning and non-reasoning tasks
by: Yu, Ping, et al.
Published: (2025)

Internal narratives parameterise affective states
by: Onysk, Jakub, et al.
Published: (2025)

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)

From Explicit CoT to Implicit CoT: Learning to Internalize CoT Step by Step
by: Deng, Yuntian, et al.
Published: (2024)

Localized Cultural Knowledge is Conserved and Controllable in Large Language Models
by: Veselovsky, Veniamin, et al.
Published: (2025)

Can LLMs perform structured graph reasoning?
by: Agrawal, Palaash, et al.
Published: (2024)

Temporal reasoning for timeline summarisation in social media
by: Song, Jiayu, et al.
Published: (2024)

Slm-mux: Orchestrating small language models for reasoning
by: Wang, Chenyu, et al.
Published: (2025)

Enhancing multimodal analogical reasoning with Logic Augmented Generation
by: Lippolis, Anna Sofia, et al.
Published: (2025)

Response: Emergent analogical reasoning in large language models
by: Hodel, Damian, et al.
Published: (2023)

Are LLMs classical or nonmonotonic reasoners? Lessons from generics
by: Leidinger, Alina, et al.
Published: (2024)

Can formal argumentative reasoning enhance LLMs performances?
by: Castagna, Federico, et al.
Published: (2024)

CARE: Cognitive-reasoning Augmented Reinforcement for Emotional Support Conversation
by: Zhu, Jie, et al.
Published: (2025)