paper-with-me

Papers

Evaluating Tokenizer Performance of Large Language Models Across Official Indian Languages

2024-11-19 · S. Tamang, D. J. Bora

Large Language Models (LLMs) based on transformer architectures have revolutionized a variety of domains, with tokenization playing a pivotal role in their pre-processing and fine-tuning stages. In multilingual models, particularly those tailored for Indic languages, effective tokenization is crucial for optimizing performance. This paper presents a comprehensive evaluation of tokenizers used by 12 LLMs across all 22 official languages of India, with a focus on comparing the efficiency of their tokenization processes. We employed the Normalized Sequence Length (NSL) as a key metric in our analysis. Our findings reveal that the SUTRA tokenizer outperforms all other models, including several Indic-specific models, excelling in 14 languages. Notable insights include the SUTRA tokenizer's superior handling of Indic languages, GPT-4o's advancement over its predecessor GPT-4 in processing Indian languages, and the limited performance of Project Indus in certain languages. This study underscores the critical importance of developing targeted tokenization strategies for multilingual and Indic-centric models, laying the groundwork for future improvements in tokenizer design to enhance linguistic coverage and model efficiency.

📄 PDF Abstract BibTeX arXiv:2411.12240

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Adam 설명 없음
Residual Connection 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…

Similar Papers 제목 키워드 기반

Beyond Text Compression: Evaluating Tokenizers Across Scales

2025-06-03 · Jonas F. Lotz, António V. Lopes, Stephan Peitz, Hendra Setiawan 외

The choice of tokenizer can profoundly impact language model performance, yet accessible and reliable evaluations of tokenizer quality remain an open challenge. Inspired by scaling consistency, we show that smaller model…

Language ModelingLanguage ModellingText Compression

Qtok: A Comprehensive Framework for Evaluating Multilingual Tokenizer Quality in Large Language Models

2024-10-16 · Iaroslav Chelombitko, Egor Safronov, Aleksey Komissarov

In the development of Large Language Models (LLMs), considerable attention has been given to the quality of training datasets. However, the role of tokenizers in the LLM training pipeline, particularly for multilingual m…

STAB: Speech Tokenizer Assessment Benchmark

2024-09-04 · Shikhar Vashishth, Harman Singh, Shikhar Bharadwaj, Sriram Ganapathy 외

Representing speech as discrete tokens provides a framework for transforming speech into a format that closely resembles text, thus enabling the use of speech as an input to the widely successful large language models (L…

Speech Tokenization

Evaluating Persian Tokenizers

2022-02-22 · Danial Kamali, Behrooz Janfada, Mohammad Ebrahim Shenasa, Behrouz Minaei-Bidgoli

Tokenization plays a significant role in the process of lexical analysis. Tokens become the input for other natural language processing tasks, like semantic parsing and language modeling. Natural Language Processing in P…

Language ModelingLanguage ModellingLexical AnalysisSemantic Parsing

Morphemes Without Borders: Evaluating Root-Pattern Morphology in Arabic Tokenizers and LLMs

2026-03-16 · Yara Alakeel, Chatrine Qwaider, Hanan Aldarmaki, Sawsan Alqahtani arxiv

This work investigates how effectively large language models (LLMs) and their tokenization schemes represent and generate Arabic root-pattern morphology, probing whether they capture genuine morphological structure or re…