2026-08-25T15:33:45Z https://drops.dagstuhl.de/oai

oai:drops-oai.dagstuhl.de:27216 2026-08-25T13:18:18Z ddc:004 open_access

Theoretical Analysis of Byte-Pair Encoding Kozma, László Voderholzer, Johannes byte pair encoding approximation hardness tokenization Byte-Pair Encoding (BPE) is a widely used method for subword tokenization, with origins in grammar-based text compression. It is employed in a variety of language processing tasks such as machine translation or large language model (LLM) pretraining, to create a token dictionary of a prescribed size. Most evaluations of BPE to date are empirical, and the reasons for its good practical performance are not well understood. In this paper we focus on the optimization problem underlying BPE: finding a pair encoding that achieves optimal compression utility. We show that this problem is APX-complete, indicating that it is unlikely to admit a polynomial-time approximation scheme. This answers, in a stronger form, a question recently raised by Zouhar et al. [Zouhar et al., 2023]. On the positive side, we show that BPE approximates the compression utility of the optimal pair encoding to a worst-case factor between 0.333 and 0.625. Our results aim to explain the ongoing success of BPE and are, to our knowledge, the first rigorous guarantees on its compression utility that hold for all inputs. Schloss Dagstuhl – Leibniz-Zentrum für Informatik László Kozma and Johannes Voderholzer 2026 Is Part Of LIPIcs, Volume 388, 34th Annual European Symposium on Algorithms (ESA 2026) InProceedings Text doc-type:ResearchArticle publishedVersion application/pdf doi:10.4230/LIPIcs.ESA.2026.80 urn:nbn:de:0030-drops-272166 https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.ESA.2026.80 eng https://creativecommons.org/licenses/by/4.0/legalcode