Related papers: Data Mixture Inference: What do BPE Tokenizers Rev…
In this work, we show a fundamental limitation in vocabulary adaptation approaches that use Byte-Pair Encoding (BPE) tokenization scheme for fine-tuning pretrained language models (PLMs) to expert domains. Current approaches trivially…
Subword regularization methods such as BPE dropout are typically applied only during fine-tuning, while pretraining is usually done with deterministic tokenization. This creates a potential segmentation mismatch between pretraining and…
Every data selection method inherently has a target. In practice, these targets often emerge implicitly through benchmark-driven iteration: researchers develop selection strategies, train models, measure benchmark performance, then refine…
Masked language modeling has become a standard pretraining objective for training encoder-based language models. In this approach, certain tokens in the input are masked, and the model learns to predict them using the surrounding context.…
Training data memorization in NLP can both be beneficial (e.g., closed-book QA) and undesirable (personal data extraction). In any case, successful model training requires a non-trivial amount of memorization to store word spellings,…
We introduce Perception Encoder (PE), a state-of-the-art vision encoder for image and video understanding trained via simple vision-language learning. Traditionally, vision encoders have relied on a variety of pretraining objectives, each…
Careful curation of data sources can significantly improve the performance of LLM pre-training, but predominant approaches rely heavily on intuition or costly trial-and-error, making them difficult to generalize across different data…
Pre-trained language models have demonstrated powerful capabilities in the field of natural language processing (NLP). Recently, code pre-trained model (PTM), which draw from the experiences of the NLP field, have also achieved…
Tokenizers play a crucial role in determining the performance, training efficiency, and the inference cost of Large Language Models (LLMs). Designing effective tokenizers for multilingual LLMs is particularly challenging due to diverse…
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…
Instruction-tuning language models has become a crucial step in aligning them for general use. Typically, this process involves extensive training on large datasets, incurring high training costs. In this paper, we introduce a novel…
In this paper, we aim to do code completion based on implementing a Neural Network from Li et. al.. Our contribution is that we use an encoding that is in-between character and word encoding called Byte Pair Encoding (BPE). We use this on…
State-of-the-art approaches for clustering high-dimensional data utilize deep auto-encoder architectures. Many of these networks require a large number of parameters and suffer from a lack of interpretability, due to the black-box nature of…
Model ensembling is a well-established technique for improving the performance of machine learning models. Conventionally, this involves averaging the output distributions of multiple models and selecting the most probable label. This idea…
NMT systems have problems with large vocabulary sizes. Byte-pair encoding (BPE) is a popular approach to solving this problem, but while BPE allows the system to generate any target-side word, it does not enable effective generalization…
The impact of subword tokenization on language model performance is well-documented for perplexity, with finer granularity consistently reducing this intrinsic metric. However, research on how different tokenization schemes affect a model's…
When used with deep learning, the symbolic music modality is often coupled with language model architectures. To do so, the music needs to be tokenized, i.e. converted into a sequence of discrete tokens. This can be achieved by different…
Estimating uncertainty in text-to-image diffusion models is challenging because of their large parameter counts (often exceeding 100 million) and operation in complex, high-dimensional spaces with virtually infinite input possibilities. In…
Byte Pair Encoding (BPE) serves as a foundation method for text tokenization in the Natural Language Processing (NLP) field. Despite its wide adoption, the original BPE algorithm harbors an inherent flaw: it inadvertently introduces a…
Generative language models are usually pretrained on large text corpus via predicting the next token (i.e., sub-word/word/phrase) given the previous ones. Recent works have demonstrated the impressive performance of large generative…