11 papers
The Effect of Scripts and Formats on LLM Numeracy
Varshini Reddy, Craig W. Schmidt, Seth Ebner +3
Large language models (LLMs) have achieved impressive proficiency in basic arithmetic, rivaling human-level performance on standard numerical tasks. However, little attention has b…
Tokenization with Split Trees
Craig W. Schmidt, Michael Krumdick, Adam Wiemerslage +4
We introduce Tokenization with Split Trees (ToaST), a subword tokenization method that directly optimizes compression under a new recursive inference procedure. ToaST greedily spli…
Universal NER v2: Towards a Massively Multilingual Named Entity Recognition Benchmark
Terra Blevins, Stephen Mayhew, Marek Å uppa +11
While multilingual language models promise to bring the benefits of LLMs to speakers of many languages, gold-standard evaluation benchmarks in most languages to interrogate these a…
Faster Superword Tokenization
Craig W. Schmidt, Chris Tanner, Yuval Pinter
Byte Pair Encoding (BPE) is a widely used tokenization algorithm, whose tokens cannot extend across pre-tokenization boundaries, functionally limiting it to representing at most fu…
The Degree of Language Diacriticity and Its Effect on Tasks
Adi Cohen, Yuval Pinter
Diacritics are orthographic marks that clarify pronunciation, distinguish similar words, or alter meaning. They play a central role in many writing systems, yet their impact on lan…
Boundless Byte Pair Encoding: Breaking the Pre-tokenization Barrier
Craig W. Schmidt, Varshini Reddy, Chris Tanner +1
Pre-tokenization, the initial step in many modern tokenization pipelines, segments text into smaller units called pretokens, typically splitting on whitespace and punctuation. Whil…