FLEXITOKENS: Flexible Tokenization for Evolving Language Models

Abraham Toluwase Owodunni, Orevaoghene Ahia, Sachin Kumar

Keywords: Bytes, Tokenization, Gradients, Segmentation, Flexible

TL;DR: Existing tokenization methods are rigid, producing fixed token segments, we propose a new method to make tokens flexible and adaptive

Abstract:

Adapting language models to new data distributions by simple finetuning is challenging. This is due to the rigidity of their subword tokenizers, which typically remain unchanged during adaptation. This inflexibility often leads to inefficient tokenization, causing overfragmentation of text in out-of-distribution domains, unseen languages, or scripts. In this work, we develop byte-level LMs with learnable tokenizers to make tokenization adaptive. Our models include a submodule that learns to predict boundaries given the input byte sequence, encoding it into variable-length segments. Most tokenizer-free methods train this boundary predictor using an auxiliary loss that enforces a fixed compression rate across the training corpus, introducing a new kind of rigidity. We propose FLEXITOKENS, a simplified training
objective that enables significantly greater flexibility during adaptation. Evaluating across multiple multilingual benchmarks, morphologically diverse tasks, and domains, we demonstrate that FLEXITOKENS consistently reduces token over-fragmentation and achieves up to 10% point improvements on token classification and generative tasks compared to BPE and other gradient-based tokenizers baselines. We validate our findings using models of varying sizes, and our method demonstrates consistent improvements across scales.

Email Sharing: We authorize the sharing of all author emails with Program Chairs.

Data Release: We authorize the release of our submission and author names to the public in the event of acceptance.

Submission Number: 80