Challenge: Despite its theoretical elegance, its implementation in practice is complex, limiting its adoption to SentencePiece.
Approach: They propose a Unigram-based probabilistic alternative to the greedy heuristics of Byte-Pair Encoding that is based on C++.
Outcome: The proposed algorithm is remarkably robust to hyperparameter choices and can be simplified to reduce computational costs.

Similar Papers

Two Counterexamples to Tokenization and the Noiseless Channel (2024.lrec-main)

Copied to clipboard

Challenge: Nevertheless, Rényi efficiency is not perfect and the metric is difficult to evaluate because training multiple tokenizers can be prohibitively expensive and takes days or weeks.
Approach: They propose to use Rényi efficiency as an intrinsic mechanism to evaluate a tokenizer for NLP tasks without the expensive step of training multiple models with different tokenizers.
Outcome: The proposed metric is better correlated to downstream model performance than a percentile frequency metric.
Tokenization Is More Than Compression (2024.emnlp-main)

Copied to clipboard

Challenge: Existing tokenization approaches like Byte-Pair Encoding (BPE) have been suggested that their effectiveness stems from their ability to condense text into a relatively small number of tokens.
Approach: They propose a tokenizer that segments a document’s text into the minimum number of tokens for a given vocabulary and propose fewer tokens to improve downstream performance.
Outcome: The proposed tokenizers can initialize vocabulary construction and pre-tokenization, and the results show that fewer tokens lead to better performance.
Stop Taking Tokenizers for Granted: They Are Core Design Decisions in Large Language Models (2026.eacl-long)

Copied to clipboard

Challenge: Subword tokenization approaches misalign with linguistic structure and waste capacity across languages and domains.
Approach: They argue for a context-aware framework that integrates tokenizer and model co-design . they argue that tokenization should be treated as a core design problem, not an afterthought .
Outcome: The proposed framework integrates tokenizer and model co-design, guided by linguistic, domain, and deployment considerations.
Analyzing Cognitive Plausibility of Subword Tokenization (2023.emnlp-main)

Copied to clipboard

Challenge: Existing evaluations of subword tokenization focus on engineering criteria such as compression rate . a recent study evaluated subwords for their cognitive plausibility in languages with limited vocabulary size .
Approach: They propose a new evaluation paradigm that focuses on the cognitive plausibility of subword tokenization.
Outcome: The proposed tokenization algorithm yields less cognitively plausible tokenization behavior and worse coverage of derivational morphemes than previous evaluations.
Byte Pair Encoding is Suboptimal for Language Model Pretraining (2020.findings-emnlp)

Copied to clipboard

Challenge: Subword tokenization is a popular language model that can be used to segment text.
Approach: They analyze differences between byte-pair encoding (BPE) and unigram LM tokenization methods to find subword units that align more closely with morphology.
Outcome: The proposed method recovers subword units that align more closely with morphology and avoids problems stemming from BPE’s greedy construction procedure.
Parity-Aware Byte-Pair Encoding: Improving Cross-lingual Fairness in Tokenization (2026.acl-long)

Copied to clipboard

Challenge: Tokenization is the first step of most NLP pipelines.
Approach: They propose a parity-aware byte pair encoder that maximizes the compression gain of the currently worst-compressed language for cross-lingual parity.
Outcome: a new algorithm reduces tokenization inequality by 89% compared to classical BPE . the proposed algorithm is based on a fair-max rule that maximizes the compression gain of the currently worst-compressed language .
Multilingual Tokenization through the Lens of Indian Languages: Challenges and Insights (2026.findings-acl)

Copied to clipboard

Challenge: Existing tokenizers are often skewed towards high-resource languages limiting their effectiveness for linguistically diverse and morphologically rich languages.
Approach: They evaluate multilingual tokenization across 17 Indic languages spanning 11 scripts and two language families.
Outcome: The proposed method improves tokenization quality and vocabulary size in 17 languages . poor tokenization can lead to increase in sequence lengths, fragment meaningful units, weaken model's ability to capture linguistic structure and semantics.
Learn Your Tokens: Word-Pooled Tokenization for Language Modeling (2023.findings-emnlp)

Copied to clipboard

Challenge: Language models typically tokenize text into subwords, using a deterministic, hand-engineered heuristic of combining characters into longer surface-level strings such as ‘ing’ or whole words.
Approach: They propose a 'learn your tokens' scheme which pooles bytes/characters into word representations and decodes individual characters/bytes per word in parallel.
Outcome: The proposed tokenizer outperforms subword models and byte/character models over the word boundary and outperformed on rare words by a factor of 30!
Where are we Still Split on Tokenization? (2024.findings-eacl)

Copied to clipboard

Challenge: Identifying tokens is a crucial first step for many tasks in Natural Language Processing (NLP) gold tokenization is often assumed, but some work on token-level tasks is more challenging.
Approach: They propose an efficient method for tokenization with subword-based language models and evaluate it on 122 languages in 20 scripts.
Outcome: The proposed method performs on par with the state-of-the-art on 122 languages in 20 scripts.
Improbable Bigrams Expose Vulnerabilities of Incomplete Tokens in Byte-Level Tokenizers (2025.emnlp-main)

Copied to clipboard

Challenge: Recent studies have revealed that tokenizers can be exploited to elicit unwanted behavior.
Approach: They propose to exploit incomplete tokens with stray bytes to exploit their dependency . they propose to use improbable bigrams to exploit the dependency of their adjacent tokens .
Outcome: The proposed tokenizers can be exploited to elicit unwanted behavior in language models.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations