相关论文: How BPE Affects Memorization in Transformers

Large pretrained self-attention neural networks, or transformers, have been very successful in various tasks recently. The performance of a model on a given task depends on its ability to memorize and generalize the training data. Large…

A significant effort has been made to train neural networks that replicate algorithmic reasoning, but they often fail to learn the abstract concepts underlying these algorithms. This is evidenced by their inability to generalize to data…

In this work, we investigate how a model's tendency to broadly integrate its parametric knowledge evolves throughout pretraining, and how this behavior affects overall performance, particularly in terms of knowledge acquisition and…

Built upon the Transformer, large language models (LLMs) have captured worldwide attention due to their remarkable abilities. Nevertheless, all Transformer-based models including LLMs suffer from a preset length limit and can hardly…

Large language models (LLMs) have been proven capable of memorizing their training data, which can be extracted through specifically designed prompts. As the scale of datasets continues to grow, privacy risks arising from memorization have…

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…

LLMs have been found to memorize training textual sequences and regurgitate verbatim said sequences during text generation time. This fact is known to be the cause of privacy and related (e.g., copyright) problems. Unlearning in LLMs then…

Efficiency and safety of Large Language Models (LLMs), among other factors, rely on the quality of tokenization. A good tokenizer not only improves inference speed and language understanding but also provides extra defense against jailbreak…

Natural language processing (NLP) tasks tend to suffer from a paucity of suitably annotated training data, hence the recent success of transfer learning across a wide variety of them. The typical recipe involves: (i) training a deep,…

Several studies have investigated the reasons behind the effectiveness of fine-tuning, usually through the lens of probing. However, these studies often neglect the role of the size of the dataset on which the model is fine-tuned. In this…

Transformer-based NLP models are trained using hundreds of millions or even billions of parameters, limiting their applicability in computationally constrained environments. While the number of parameters generally correlates with…

Recent large-scale natural language processing (NLP) systems use a pre-trained Large Language Model (LLM) on massive and diverse corpora as a headstart. In practice, the pre-trained model is adapted to a wide array of tasks via fine-tuning…

The Transformer model is widely successful on many natural language processing tasks. However, the quadratic complexity of self-attention limit its application on long text. In this paper, adopting a fine-to-coarse attention mechanism on…

Word embeddings are a powerful approach for analyzing language and have been widely popular in numerous tasks in information retrieval and text mining. Training embeddings over huge corpora is computationally expensive because the input is…

Large language models have gained significant popularity because of their ability to generate human-like text and potential applications in various fields, such as Software Engineering. Large language models for code are commonly trained on…

Pretrained language models are typically trained on massive web-based datasets, which are often "contaminated" with downstream test sets. It is not clear to what extent models exploit the contaminated data for downstream tasks. We present a…

Large Language Models (LLMs) have demonstrated remarkable capabilities across a wide range of tasks, yet they also exhibit memorization of their training data. This phenomenon raises critical questions about model behavior, privacy risks,…

Modern approaches to enhancing Large Language Models' factual accuracy and knowledge utilization face a fundamental trade-off: non-parametric retrieval-augmented generation (RAG) provides flexible access to external knowledge but suffers…

Tokenization is a fundamental component of large language models (LLMs), yet its influence on model scaling and performance is not fully explored. In this paper, we introduce Over-Tokenized Transformers, a novel framework that decouples…

Large language models (LLMs) cannot be trusted for economic forecasts during periods covered by their training data. Counterfactual forecasting ability is non-identified when the model has seen the realized values: any observed output is…