Buchumschlag

Counting Ability of Large Language Models and Impact of Tokenization

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Zhang, Xiang, Cao, Juntai, You, Chenyu
Format:	Preprint
Veröffentlicht:	2024
Schlagworte:	Computation and Language Artificial Intelligence
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

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

Every Token Counts: Generalizing 16M Ultra-Long Context in Large Language Models
von: Hu, Xiang, et al.
Veröffentlicht: (2025)

On the Decision-Making Abilities in Role-Playing using Large Language Models
von: Shen, Chenglei, et al.
Veröffentlicht: (2024)

PersonaLLM: Investigating the Ability of Large Language Models to Express Personality Traits
von: Jiang, Hang, et al.
Veröffentlicht: (2023)

Reflection Pretraining Enables Token-Level Self-Correction in Biological Sequence Models
von: Zhang, Xiang, et al.
Veröffentlicht: (2025)

Editing Factual Knowledge and Explanatory Ability of Medical Large Language Models
von: Xu, Derong, et al.
Veröffentlicht: (2024)

Eliciting Causal Abilities in Large Language Models for Reasoning Tasks
von: Wang, Yajing, et al.
Veröffentlicht: (2024)

Large Language Models have Intrinsic Self-Correction Ability
von: Liu, Dancheng, et al.
Veröffentlicht: (2024)

Investigating Large Language Models' Linguistic Abilities for Text Preprocessing
von: Braga, Marco, et al.
Veröffentlicht: (2025)

A Closer Look at the Self-Verification Abilities of Large Language Models in Logical Reasoning
von: Hong, Ruixin, et al.
Veröffentlicht: (2023)

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

Emergent Abilities of Large Language Models under Continued Pretraining for Language Adaptation
von: Elhady, Ahmed, et al.
Veröffentlicht: (2025)

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

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

A Survey on Enhancing Causal Reasoning Ability of Large Language Models
von: Li, Xin, et al.
Veröffentlicht: (2025)

Towards Reasoning Ability of Small Language Models
von: Srivastava, Gaurav, et al.
Veröffentlicht: (2025)

Exploring the Reasoning Abilities of Multimodal Large Language Models (MLLMs): A Comprehensive Survey on Emerging Trends in Multimodal Reasoning
von: Wang, Yiqi, et al.
Veröffentlicht: (2024)

RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language Models
von: Wang, Zekun Moore, et al.
Veröffentlicht: (2023)

Deception Abilities Emerged in Large Language Models
von: Hagendorff, Thilo
Veröffentlicht: (2023)

Memory Retrieval and Consolidation in Large Language Models through Function Tokens
von: Zhang, Shaohua, et al.
Veröffentlicht: (2025)

TEAL: Tokenize and Embed ALL for Multi-modal Large Language Models
von: Yang, Zhen, et al.
Veröffentlicht: (2023)

Code-driven Number Sequence Calculation: Enhancing the inductive Reasoning Abilities of Large Language Models
von: Chen, Kedi, et al.
Veröffentlicht: (2025)

Toward Graph-Tokenizing Large Language Models with Reconstructive Graph Instruction Tuning
von: Zhang, Zhongjian, et al.
Veröffentlicht: (2026)

FinDABench: Benchmarking Financial Data Analysis Ability of Large Language Models
von: Liu, Shu, et al.
Veröffentlicht: (2024)

InFoBench: Evaluating Instruction Following Ability in Large Language Models
von: Qin, Yiwei, et al.
Veröffentlicht: (2024)

LogicGame: Benchmarking Rule-Based Reasoning Abilities of Large Language Models
von: Gui, Jiayi, et al.
Veröffentlicht: (2024)

Ensembling Large Language Models to Characterize Affective Dynamics in Student-AI Tutor Dialogues
von: Zhang, Chenyu, et al.
Veröffentlicht: (2025)

Psychological Counseling Ability of Large Language Models
von: Peng, Fangyu, et al.
Veröffentlicht: (2025)

Do We Need Distinct Representations for Every Speech Token? Unveiling and Exploiting Redundancy in Large Speech Language Models
von: Xiang, Bajian, et al.
Veröffentlicht: (2026)

Exposing Numeracy Gaps: A Benchmark to Evaluate Fundamental Numerical Abilities in Large Language Models
von: Li, Haoyang, et al.
Veröffentlicht: (2025)

IDEA: Enhancing the Rule Learning Ability of Large Language Model Agent through Induction, Deduction, and Abduction
von: He, Kaiyu, et al.
Veröffentlicht: (2024)

Reasoning Can Hurt the Inductive Abilities of Large Language Models
von: Jin, Haibo, et al.
Veröffentlicht: (2025)

Self-Evolving Critique Abilities in Large Language Models
von: Tang, Zhengyang, et al.
Veröffentlicht: (2025)

Emergent Abilities in Large Language Models: A Survey
von: Berti, Leonardo, et al.
Veröffentlicht: (2025)

When Every Token Counts: Optimal Segmentation for Low-Resource Language Models
von: Raj, Bharath, et al.
Veröffentlicht: (2024)

Full-ECE: A Metric For Token-level Calibration on Large Language Models
von: Liu, Han, et al.
Veröffentlicht: (2024)

Orca: Enhancing Role-Playing Abilities of Large Language Models by Integrating Personality Traits
von: Huang, Yuxuan
Veröffentlicht: (2024)

Embedding Self-Correction as an Inherent Ability in Large Language Models for Enhanced Mathematical Reasoning
von: Gao, Kuofeng, et al.
Veröffentlicht: (2024)

LogicBench: Towards Systematic Evaluation of Logical Reasoning Ability of Large Language Models
von: Parmar, Mihir, et al.
Veröffentlicht: (2024)

U-shaped and Inverted-U Scaling behind Emergent Abilities of Large Language Models
von: Wu, Tung-Yu, et al.
Veröffentlicht: (2024)