Cover Image

State over Tokens: Characterizing the Role of Reasoning Tokens

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Levy, Mosh, Elyoseph, Zohar, Ravfogel, Shauli, Goldberg, Yoav
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Humans Perceive Wrong Narratives from AI Reasoning Texts
by: Levy, Mosh, et al.
Published: (2025)

Same Task, More Tokens: the Impact of Input Length on the Reasoning Performance of Large Language Models
by: Levy, Mosh, et al.
Published: (2024)

Knowledge Navigator: LLM-guided Browsing Framework for Exploratory Search in Scientific Literature
by: Katz, Uri, et al.
Published: (2024)

Log-linear Guardedness and its Implications
by: Ravfogel, Shauli, et al.
Published: (2022)

BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models
by: Ben-Zaken, Elad, et al.
Published: (2021)

A Practical Method for Generating String Counterfactuals
by: Avitan, Matan, et al.
Published: (2024)

Kernelized Concept Erasure
by: Ravfogel, Shauli, et al.
Published: (2022)

Linear Adversarial Concept Erasure
by: Ravfogel, Shauli, et al.
Published: (2022)

Gumbel Counterfactual Generation From Language Models
by: Ravfogel, Shauli, et al.
Published: (2024)

Intrinsic Test of Unlearning Using Parametric Knowledge Traces
by: Hong, Yihuai, et al.
Published: (2024)

Diversity Over Quantity: A Lesson From Few Shot Relation Classification
by: Cohen, Amir DN, et al.
Published: (2024)

Do AI Voices Learn Social Nuances? A Case of Politeness and Speech Rate
by: Rabin, Eyal, et al.
Published: (2025)

Compared to What? Baselines and Metrics for Counterfactual Prompting
by: Yang, Zihao, et al.
Published: (2026)

Description-Based Text Similarity
by: Ravfogel, Shauli, et al.
Published: (2023)

Linguistic Binding in Diffusion Models: Enhancing Attribute Correspondence through Attention Map Alignment
by: Rassin, Royi, et al.
Published: (2023)

Extending Token Computation for LLM Reasoning
by: Liao, Bingli, et al.
Published: (2024)

Simple Linguistic Inferences of Large Language Models (LLMs): Blind Spots and Blinds
by: Basmov, Victoria, et al.
Published: (2023)

Learning to Reason with Mixture of Tokens
by: Jain, Adit, et al.
Published: (2025)

A Token is Worth over 1,000 Tokens: Efficient Knowledge Distillation through Low-Rank Clone
by: Hao, Jitai, et al.
Published: (2025)

From Language Models over Tokens to Language Models over Characters
by: Vieira, Tim, et al.
Published: (2024)

Say Anything but This: When Tokenizer Betrays Reasoning in LLMs
by: Ayoobi, Navid, et al.
Published: (2026)

The Token Tax: Systematic Bias in Multilingual Tokenization
by: Lundin, Jessica M., et al.
Published: (2025)

Token-Budget-Aware LLM Reasoning
by: Han, Tingxu, et al.
Published: (2024)

Date Fragments: A Hidden Bottleneck of Tokenization for Temporal Reasoning
by: Bhatia, Gagan, et al.
Published: (2025)

SelfBudgeter: Adaptive Token Allocation for Efficient LLM Reasoning
by: Li, Zheng, et al.
Published: (2025)

Critical Tokens Matter: Token-Level Contrastive Estimation Enhances LLM's Reasoning Capability
by: Lin, Zicheng, et al.
Published: (2024)

Demystifying Reasoning Dynamics with Mutual Information: Thinking Tokens are Information Peaks in LLM Reasoning
by: Qian, Chen, et al.
Published: (2025)

Can LLMs Introspect? A Reality Check
by: Singh, Shashwat, et al.
Published: (2026)

Diagnosing Memorization in Chain-of-Thought Reasoning, One Token at a Time
by: Li, Huihan, et al.
Published: (2025)

Tokenization Constraints in LLMs: A Study of Symbolic and Arithmetic Reasoning Limits
by: Zhang, Xiang, et al.
Published: (2025)

HeartLLM: Discretized ECG Tokenization for LLM-Based Diagnostic Reasoning
by: Yang, Jinning, et al.
Published: (2025)

SD-E$^2$: Semantic Exploration for Reasoning Under Token Budgets
by: Mishra, Kshitij, et al.
Published: (2026)

Tokenization Matters! Degrading Large Language Models through Challenging Their Tokenization
by: Wang, Dixuan, et al.
Published: (2024)

Guiding Language Model Reasoning with Planning Tokens
by: Wang, Xinyi, et al.
Published: (2023)

Token Assorted: Mixing Latent and Text Tokens for Improved Language Model Reasoning
by: Su, DiJia, et al.
Published: (2025)

Rethinking Tokenization for Rich Morphology: The Dominance of Unigram over BPE and Morphological Alignment
by: Vemula, Saketh Reddy, et al.
Published: (2025)

HeQ: a Large and Diverse Hebrew Reading Comprehension Benchmark
by: Cohen, Amir DN, et al.
Published: (2025)

TokenButler: Token Importance is Predictable
by: Akhauri, Yash, et al.
Published: (2025)

SemToken: Semantic-Aware Tokenization for Efficient Long-Context Language Modeling
by: Liu, Dong, et al.
Published: (2025)

One Token Is Enough: Improving Diffusion Language Models with a Sink Token
by: Zhang, Zihou, et al.
Published: (2026)