Related papers: BPE Stays on SCRIPT: Structured Encoding for Robus…

Recent advances in generative AI have been largely driven by large language models (LLMs), deep neural networks that operate over discrete units called tokens. To represent text, the vast majority of LLMs use words or word fragments as the…

We propose a generalization of neural network sequence models. Instead of predicting one symbol at a time, our multi-scale model makes predictions over multiple, potentially overlapping multi-symbol tokens. A variation of the byte-pair…

Tokenizing raw texts into word units is an essential pre-processing step for critical tasks in the NLP pipeline such as tagging, parsing, named entity recognition, and more. For most languages, this tokenization step straightforward.…

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 biases that the…

Soft prompts have emerged as a powerful alternative to adapters in parameter-efficient fine-tuning (PEFT), enabling large language models (LLMs) to adapt to downstream tasks without architectural changes or parameter updates. While prior…

Traditionally, NLP performance improvement has been focused on improving models and increasing the number of model parameters. NLP vocabulary construction has remained focused on maximizing the number of words represented through subword…

Tokenization is associated with many poorly understood shortcomings in language models (LMs), yet remains an important component for long sequence scaling purposes. This work studies how tokenization impacts model performance by analyzing…

Most neural machine translation systems are built upon subword units extracted by methods such as Byte-Pair Encoding (BPE) or wordpiece. However, the choice of number of merge operations is generally made by following existing recipes. In…

Subword tokenization is a common method for vocabulary building in Neural Machine Translation (NMT) models. However, increasingly complex tasks have revealed its disadvantages. First, a vocabulary cannot be modified once it is learned,…

The attention mechanism is a critical component of Large Language Models (LLMs) that allows tokens in a sequence to interact with each other, but is order-invariant. Incorporating position encoding (PE) makes it possible to address by…

We present the KL3M tokenizers, a family of specialized tokenizers for legal, financial, and governmental text. Despite established work on tokenization, specialized tokenizers for professional domains remain understudied. Our paper offers…

Language Reasoning Models (LRMs) achieve strong performance by scaling test-time computation but often suffer from ``overthinking'', producing excessively long reasoning traces that increase latency and memory usage. Existing LRMs typically…

Multimodal large language models (MLLMs) have made significant progress in vision-language understanding, yet effectively aligning different modalities remains a fundamental challenge. We present a framework that unifies multimodal…

This paper details the methodology behind CoPE, a policy-steerable small language model capable of fast and accurate content labeling. We present a novel training curricula called Contradictory Example Training that enables the model to…

The dramatic increase of data breaches in modern computing platforms has emphasized that access control is not sufficient to protect sensitive user data. Recent advances in cryptography allow end-to-end processing of encrypted data without…

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…

Tokenization is a hardcoded compression step which remains in the training pipeline of Large Language Models (LLMs), despite a general trend towards architectures becoming increasingly end-to-end. Prior work has shown promising results at…

We investigate tokenization strategies for Kurdish word embeddings by comparing word-level, morpheme-based, and BPE approaches on morphological similarity preservation tasks. We develop a BiLSTM-CRF morphological segmenter using…

Tokenization plays a pivotal role in multilingual NLP. However, existing tokenizers are often skewed towards high-resource languages, limiting their effectiveness for linguistically diverse and morphologically rich languages such as those…

This paper presents a novel hybrid tokenization strategy that enhances the performance of DNA Language Models (DLMs) by combining 6-mer tokenization with Byte Pair Encoding (BPE-600). Traditional k-mer tokenization is effective at capturing…