[YossarianFrPrez]

This is a cool paper!

Basically, prior to feeding text to the tokenizer people have split the text on whitespaces. But whitespaces aren't exactly meaningful separators. By getting rid of this restriction as the tokenizer is 'learning', some of the tokens end up being 'by the way' or 'in the the long run.' The researchers find that this makes the model much more efficient.

[yuvalpinter]

This can also be done within the tokenization framework, see our work here: https://arxiv.org/abs/2504.00178

[woodson]

How does this differ from SuperBPE, which seems to pursue a similar goal? https://arxiv.org/abs/2503.13423

Looks like parallel invention. (I’m not associated with the paper or its authors.)

[anonymoushn]

In SuperBPE, a fixed number of tokens are learned, and then the constraints of pretokenization are removed entirely, and then the remainder of the target vocab size is learned.

In Boundless BPE, no schedule must be chosen, because there is not any point at which the constraints of pretokenization are removed entirely. Instead, at any point in the learning process, merges between adjacent pretokens are permitted if the pretokens are each represented by a single token. There are some additional details about how the authors incorporate Picky BPE, which I will not try to repeat because I would probably get them wrong.

[cschmidt]

Yes, they were concurrent work. (Co-author of BoundlessBPE here). A sibling comment describes the main differences. Our paper motivates why superwords can lead to such a big improvement, by overcoming a limit that pre-tokenization imposes on current tokenization methods. The SuperBPE paper has a wonderful set of downstream evaluation runs. So if you're interested in either, they are quite complimentary papers.