Cover Image

Reasoning Models Know What's Important, and Encode It in Their Activations

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Nikankin, Yaniv, Tutek, Martin, Ashuach, Tomer, Rosenfeld, Jonathan, Belinkov, Yonatan
Format:	Preprint
Published:	2026
Subjects:	Computation and Language 68T5 I.2.7
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

REVS: Unlearning Sensitive Information in Language Models via Rank Editing in the Vocabulary Space
by: Ashuach, Tomer, et al.
Published: (2024)

Arithmetic Without Algorithms: Language Models Solve Math With a Bag of Heuristics
by: Nikankin, Yaniv, et al.
Published: (2024)

Same Task, Different Circuits: Disentangling Modality-Specific Mechanisms in VLMs
by: Nikankin, Yaniv, et al.
Published: (2025)

CRISP: Persistent Concept Unlearning via Sparse Autoencoders
by: Ashuach, Tomer, et al.
Published: (2025)

Masked by Consensus: Disentangling Privileged Knowledge in LLM Correctness
by: Ashuach, Tomer, et al.
Published: (2026)

ManagerBench: Evaluating the Safety-Pragmatism Trade-off in Autonomous LLMs
by: Simhi, Adi, et al.
Published: (2025)

LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations
by: Orgad, Hadas, et al.
Published: (2024)

ReFACT: Updating Text-to-Image Models by Editing the Text Encoder
by: Arad, Dana, et al.
Published: (2023)

Old Habits Die Hard: How Conversational History Geometrically Traps LLMs
by: Simhi, Adi, et al.
Published: (2026)

Trust Me, I'm Wrong: LLMs Hallucinate with Certainty Despite Knowing the Answer
by: Simhi, Adi, et al.
Published: (2025)

Position-aware Automatic Circuit Discovery
by: Haklay, Tal, et al.
Published: (2025)

Distinguishing Ignorance from Error in LLM Hallucinations
by: Simhi, Adi, et al.
Published: (2024)

Constructing Benchmarks and Interventions for Combating Hallucinations in LLMs
by: Simhi, Adi, et al.
Published: (2024)

Are formal and functional linguistic mechanisms dissociated in language models?
by: Hanna, Michael, et al.
Published: (2025)

Multilingual Multi-Label Emotion Classification at Scale with Synthetic Data
by: Borisov, Vadim
Published: (2026)

Transparent but Powerful: Explainability, Accuracy, and Generalizability in ADHD Detection from Social Media Data
by: Wiechmann, D., et al.
Published: (2024)

What is Wrong with Language Models that Can Not Tell a Story?
by: Yamshchikov, Ivan P., et al.
Published: (2022)

Have Faith in Faithfulness: Going Beyond Circuit Overlap When Finding Model Mechanisms
by: Hanna, Michael, et al.
Published: (2024)

Enhancing OCR for Sino-Vietnamese Language Processing via Fine-tuned PaddleOCRv5
by: Nguyen, Minh Hoang, et al.
Published: (2025)

Do LLMs Know What They Know? Measuring Metacognitive Efficiency with Signal Detection Theory
by: Cacioli, Jon-Paul
Published: (2026)

Logits-Constrained Framework with RoBERTa for Ancient Chinese NER
by: Hua, Wenjie, et al.
Published: (2025)

A Dataset for Metaphor Detection in Early Medieval Hebrew Poetry
by: Toker, Michael, et al.
Published: (2024)

ECLAIR: Enhanced Clarification for Interactive Responses in an Enterprise AI Assistant
by: Murzaku, John, et al.
Published: (2025)

CLMN: Concept based Language Models via Neural Symbolic Reasoning
by: Yang, Yibo
Published: (2025)

Can LLMs Compute with Reasons?
by: Sandilya, Harshit, et al.
Published: (2024)

Vis-CoT: A Human-in-the-Loop Framework for Interactive Visualization and Intervention in LLM Chain-of-Thought Reasoning
by: Pather, Kaviraj, et al.
Published: (2025)

Beyond Subtokens: A Rich Character Embedding for Low-resource and Morphologically Complex Languages
by: Schneider, Felix, et al.
Published: (2026)

Co-NAML-LSTUR: A Combined Model with Attentive Multi-View Learning and Long- and Short-term User Representations for News Recommendation
by: Nguyen, Minh Hoang, et al.
Published: (2025)

Improving French Synthetic Speech Quality via SSML Prosody Control
by: Ouali, Nassima Ould, et al.
Published: (2025)

New Skills or Sharper Primitives? A Probabilistic Perspective on the Emergence of Reasoning in RLVR
by: Wang, Zhilin, et al.
Published: (2026)

Multi-Agent Synergy-Driven Iterative Visual Narrative Synthesis
by: Xi, Wang, et al.
Published: (2025)

Culturally-Nuanced Story Generation for Reasoning in Low-Resource Languages: The Case of Javanese and Sundanese
by: Pranida, Salsabila Zahirah, et al.
Published: (2025)

Optimizing What We Trust: Reliability-Guided QUBO Selection of Multi-Agent Weak Framing Signals for Arabic Sentiment Prediction
by: Alkhalifa, Rabab
Published: (2026)

Rethinking the Multilingual Reasoning Gap with Layer Swap
by: Lasbordes, Maxence, et al.
Published: (2026)

Growing a Tail: Increasing Output Diversity in Large Language Models
by: Shur-Ofry, Michal, et al.
Published: (2024)

Evaluating GenAI for Simplifying Texts for Education: Improving Accuracy and Consistency for Enhanced Readability
by: Day, Stephanie L., et al.
Published: (2025)

PaperAudit-Bench: Benchmarking Error Detection in Research Papers for Critical Automated Peer Review
by: Tu, Songjun, et al.
Published: (2026)

D-SMART: Enhancing LLM Dialogue Consistency via Dynamic Structured Memory And Reasoning Tree
by: Lei, Xiang, et al.
Published: (2025)

Thinking Longer, Not Always Smarter: Evaluating LLM Capabilities in Hierarchical Legal Reasoning
by: Zhang, Li, et al.
Published: (2025)

HACK: Hallucinations Along Certainty and Knowledge Axes
by: Simhi, Adi, et al.
Published: (2025)