LangMAP: A Language-Adaptive Approach to Tokenization
Language-specific tokenizers improve tokenization quality and the downstream performance of models on those languages. However, using such a tokenizer comes at a cost: either a new model must be trained from scratch, or the vocabulary of an existing pretrained model must be adapted. We propose Language-adaptive Maximum a Posteriori (LangMAP) Tokenization, a tokenization scheme that extends the UnigramLM algorithm to the multilingual setting, producing language-specific tokenization from a single shared vocabulary. Notably, LangMAP can be used when training a multilingual language model from scratch or to adapt a pretrained model's tokenizer to individual languages without changing its vocabulary. While language labels are required at training time, a key feature of the algorithm is that it then performs language-specific tokenization at inference without knowledge of the input's language. Across 14 open-source tokenizers, 9 natural languages, and 9 programming languages, LangMAP improves morphological boundary alignment and, for all coding languages tested, alignment with abstract syntax tree (AST) leaf boundaries. In fine-tuning experiments, results are mixed: LangMAP improves target-language grammatical acceptability (MultiBLiMP) on the languages tested; its benefits are less consistent on knowledge-related tasks (Global-PIQA, Belebele).
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
LangMap: A Human-Verified Benchmark for Hierarchical Open-Vocabulary Goal Navigation
Language-conditioned goal navigation (LGN) requires agents to locate user-specified targets without step-by-step guidance. However, existing benchmarks largely focus on category-level goals or rely on instance descriptio…
Task-Adaptive Tokenization: Enhancing Long-Form Text Generation Efficacy in Mental Health and Beyond
We propose task-adaptive tokenization as a way to adapt the generation pipeline to the specifics of a downstream task and enhance long-form generation in mental health. Inspired by insights from cognitive science, our ta…
FormQuestion AnsweringText GenerationMAGNET: Improving the Multilingual Fairness of Language Models with Adaptive Gradient-Based Tokenization
In multilingual settings, non-Latin scripts and low-resource languages are usually disadvantaged in terms of language models' utility, efficiency, and cost. Specifically, previous studies have reported multiple modeling …
FairnessLanguage ModellingSegmentationTokenization Disparities as Infrastructure Bias: How Subword Systems Create Inequities in LLM Access and Efficiency
Tokenization disparities pose a significant barrier to achieving equitable access to artificial intelligence across linguistically diverse populations. This study conducts a large-scale cross-linguistic evaluation of tok…
DNACHUNKER: Learnable Tokenization for DNA Language Models
DNA language models are increasingly used to represent genomic sequence, yet their effectiveness depends critically on how raw nucleotides are converted into model inputs. Unlike natural language, DNA offers no canonical…