IndicSuperTokenizer: An Optimized Tokenizer for Indic Multilingual LLMs

• URL: http://arxiv.org/abs/2511.03237v1
• Date: Wed, 05 Nov 2025 06:57:42 GMT
• Title: IndicSuperTokenizer: An Optimized Tokenizer for Indic Multilingual LLMs
• Authors: Souvik Rana, Arul Menezes, Ashish Kulkarni, Chandra Khatri, Shubham Agarwal,
• Abstract summary: IndicSuperTokenizer is a tokenizer for Indic multilingual LLMs.<n>It combines subword and multi-word tokenization, along with language-specific tokens pre-tokenization.<n>It improves the average fertility score by 39.5% over LLaMA4 and by 18% over Sutra.
• Score: 5.068673710249497
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Tokenizers play a crucial role in determining the performance, training efficiency, and the inference cost of Large Language Models (LLMs). Designing effective tokenizers for multilingual LLMs is particularly challenging due to diverse scripts and rich morphological variation. While subword methods such as Byte Pair Encoding (BPE) are widely adopted, their effectiveness in multilingual settings remains underexplored. We present IndicSuperTokenizer, a tokenizer for Indic multilingual LLMs, that combines both subword and multi-word tokenization, along with language-specific pre-tokenization, leading to more linguistically aligned tokens and achieving a new state-of-the-art in fertility score. Evaluated across English, 22 Indian languages and code data, our tokenizer improves the average fertility score by 39.5% over LLaMA4 and by 18% over Sutra (the current best). This translates to 44% improvement in inference throughput over LLaMA4 while maintaining comparable performance on English and Indic benchmarks. We also present detailed ablations across tokenizer training data size, vocabulary size, merging techniques, and pre-tokenization strategies, demonstrating the robustness of our design choices.

Related papers

• What Language is This? Ask Your Tokenizer [32.28976119949841]
  Language Identification (LID) is an important component of many multilingual natural language processing pipelines.<n>We introduce UniLID, a simple and efficient LID method based on the UnigramLM tokenization algorithm.<n>Our formulation is data- and compute-efficient, supports incremental addition of new languages without retraining existing models.
  arXiv  Detail & Related papers  (2026-02-19T18:58:39Z)
• Multilingual Tokenization through the Lens of Indian Languages: Challenges and Insights [27.369278566345074]
  This paper presents an intrinsic evaluation of tokenization strategies across 17 Indian languages.<n>We quantify the trade-offs between bottom-up and top-down tokenizer algorithms.<n>We show that extremely low-resource languages can benefit from tokenizers trained on related high-resource languages.
  arXiv  Detail & Related papers  (2025-06-21T18:47:33Z)
• Evaluating Tokenizer Performance of Large Language Models Across Official Indian Languages [0.0]
  This paper presents a comprehensive evaluation of tokenizers used by 12 Large Language Models (LLMs) across all 22 official languages of India. The SUTRA tokenizer outperforms all other models, including several Indic-specific models, excelling in 14 languages. This study underscores the critical importance of developing targeted tokenization strategies for multilingual and Indic-centric models.
  arXiv  Detail & Related papers  (2024-11-19T05:37:17Z)
• Parrot: Multilingual Visual Instruction Tuning [66.65963606552839]
  Existing methods typically align vision encoders with Multimodal Large Language Models (MLLMs) via supervised fine-tuning (SFT)<n>We propose PARROT, a novel approach that leverages textual guidance for visual token alignment at the language level.<n>We introduce the Massive Multilingual Multimodal Benchmark (MMMB), a new benchmark comprising 6 languages, 15 categories, and 12,000 questions.
  arXiv  Detail & Related papers  (2024-06-04T17:56:28Z)
• Decomposed Prompting: Probing Multilingual Linguistic Structure Knowledge in Large Language Models [54.58989938395976]
  We introduce a decomposed prompting approach for sequence labeling tasks.<n>We test our method on the Universal Dependencies part-of-speech tagging dataset for 38 languages.
  arXiv  Detail & Related papers  (2024-02-28T15:15:39Z)
• Romanization-based Large-scale Adaptation of Multilingual Language Models [124.57923286144515]
  Large multilingual pretrained language models (mPLMs) have become the de facto state of the art for cross-lingual transfer in NLP. We study and compare a plethora of data- and parameter-efficient strategies for adapting the mPLMs to romanized and non-romanized corpora of 14 diverse low-resource languages. Our results reveal that UROMAN-based transliteration can offer strong performance for many languages, with particular gains achieved in the most challenging setups.
  arXiv  Detail & Related papers  (2023-04-18T09:58:34Z)
• Efficiently Aligned Cross-Lingual Transfer Learning for Conversational Tasks using Prompt-Tuning [98.60739735409243]
  Cross-lingual transfer of language models trained on high-resource languages like English has been widely studied for many NLP tasks. We introduce XSGD for cross-lingual alignment pretraining, a parallel and large-scale multilingual conversation dataset. To facilitate aligned cross-lingual representations, we develop an efficient prompt-tuning-based method for learning alignment prompts.
  arXiv  Detail & Related papers  (2023-04-03T18:46:01Z)
• Multi-level Contrastive Learning for Cross-lingual Spoken Language Understanding [90.87454350016121]
  We develop novel code-switching schemes to generate hard negative examples for contrastive learning at all levels. We develop a label-aware joint model to leverage label semantics for cross-lingual knowledge transfer.
  arXiv  Detail & Related papers  (2022-05-07T13:44:28Z)
• Exposing Cross-Lingual Lexical Knowledge from Multilingual Sentence Encoders [85.80950708769923]
  We probe multilingual language models for the amount of cross-lingual lexical knowledge stored in their parameters, and compare them against the original multilingual LMs. We also devise a novel method to expose this knowledge by additionally fine-tuning multilingual models. We report substantial gains on standard benchmarks.
  arXiv  Detail & Related papers  (2022-04-30T13:23:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.