Subword tokenization has become the de-facto standard for tokenization, although comparative evaluations of subword vocabulary quality across languages are scarce. Existing evaluation studies focus on the effect of a tokenization algorithm on the performance in downstream tasks, or on engineering criteria such as the compression rate. We present a new evaluation paradigm that focuses on the cognitive plausibility of subword tokenization. We analyze the correlation of the tokenizer output with the response time and accuracy of human performance on a lexical decision task. We compare three tokenization algorithms across several languages and vocabulary sizes. Our results indicate that the UnigramLM algorithm yields less cognitively plausible tokenization behavior and a worse coverage of derivational morphemes, in contrast with prior work.
相關內容
As an emerging federated learning paradigm, federated distillation enables communication-efficient model training by transmitting only small-scale knowledge during the learning process. To further improve the communication efficiency of federated distillation, we propose a novel technique, ALU, which accumulates multiple rounds of local updates before transferring the knowledge to the central server. ALU drastically decreases the frequency of communication in federated distillation, thereby significantly reducing the communication overhead during the training process. Empirical experiments demonstrate the substantial effect of ALU in improving the communication efficiency of federated distillation.
Molecular Property Prediction (MPP) task involves predicting biochemical properties based on molecular features, such as molecular graph structures, contributing to the discovery of lead compounds in drug development. To address data scarcity and imbalance in MPP, some studies have adopted Graph Neural Networks (GNN) as an encoder to extract commonalities from molecular graphs. However, these approaches often use a separate predictor for each task, neglecting the shared characteristics among predictors corresponding to different tasks. In response to this limitation, we introduce the GNN-MoCE architecture. It employs the Mixture of Collaborative Experts (MoCE) as predictors, exploiting task commonalities while confronting the homogeneity issue in the expert pool and the decision dominance dilemma within the expert group. To enhance expert diversity for collaboration among all experts, the Expert-Specific Projection method is proposed to assign a unique projection perspective to each expert. To balance decision-making influence for collaboration within the expert group, the Expert-Specific Loss is presented to integrate individual expert loss into the weighted decision loss of the group for more equitable training. Benefiting from the enhancements of MoCE in expert creation, dynamic expert group formation, and experts' collaboration, our model demonstrates superior performance over traditional methods on 24 MPP datasets, especially in tasks with limited data or high imbalance.
Quantum programs are notoriously difficult to code and verify due to unintuitive quantum knowledge associated with quantum programming. Automated tools relieving the tedium and errors associated with low-level quantum details would hence be highly desirable. In this paper, we initiate the study of program synthesis for quantum unitary programs that recursively define a family of unitary circuits for different input sizes, which are widely used in existing quantum programming languages. Specifically, we present QSynth, the first quantum program synthesis framework, including a new inductive quantum programming language, its specification, a sound logic for reasoning, and an encoding of the reasoning procedure into SMT instances. By leveraging existing SMT solvers, QSynth successfully synthesizes ten quantum unitary programs including quantum adder circuits, quantum eigenvalue inversion circuits and Quantum Fourier Transformation, which can be readily transpiled to executable programs on major quantum platforms, e.g., Q#, IBM Qiskit, and AWS Braket.
We propose an auditing method to identify whether a large language model (LLM) encodes patterns such as hallucinations in its internal states, which may propagate to downstream tasks. We introduce a weakly supervised auditing technique using a subset scanning approach to detect anomalous patterns in LLM activations from pre-trained models. Importantly, our method does not need knowledge of the type of patterns a-priori. Instead, it relies on a reference dataset devoid of anomalies during testing. Further, our approach enables the identification of pivotal nodes responsible for encoding these patterns, which may offer crucial insights for fine-tuning specific sub-networks for bias mitigation. We introduce two new scanning methods to handle LLM activations for anomalous sentences that may deviate from the expected distribution in either direction. Our results confirm prior findings of BERT's limited internal capacity for encoding hallucinations, while OPT appears capable of encoding hallucination information internally. Importantly, our scanning approach, without prior exposure to false statements, performs comparably to a fully supervised out-of-distribution classifier.
Understanding the similarity of the numerous released large language models (LLMs) has many uses, e.g., simplifying model selection, detecting illegal model reuse, and advancing our understanding of what makes LLMs perform well. In this work, we measure the similarity of representations of a set of LLMs with 7B parameters. Our results suggest that some LLMs are substantially different from others. We identify challenges of using representational similarity measures that suggest the need of careful study of similarity scores to avoid false conclusions.
Large Language Models (LLMs) have shown excellent generalization capabilities that have led to the development of numerous models. These models propose various new architectures, tweaking existing architectures with refined training strategies, increasing context length, using high-quality training data, and increasing training time to outperform baselines. Analyzing new developments is crucial for identifying changes that enhance training stability and improve generalization in LLMs. This survey paper comprehensively analyses the LLMs architectures and their categorization, training strategies, training datasets, and performance evaluations and discusses future research directions. Moreover, the paper also discusses the basic building blocks and concepts behind LLMs, followed by a complete overview of LLMs, including their important features and functions. Finally, the paper summarizes significant findings from LLM research and consolidates essential architectural and training strategies for developing advanced LLMs. Given the continuous advancements in LLMs, we intend to regularly update this paper by incorporating new sections and featuring the latest LLM models.
Residual networks (ResNets) have displayed impressive results in pattern recognition and, recently, have garnered considerable theoretical interest due to a perceived link with neural ordinary differential equations (neural ODEs). This link relies on the convergence of network weights to a smooth function as the number of layers increases. We investigate the properties of weights trained by stochastic gradient descent and their scaling with network depth through detailed numerical experiments. We observe the existence of scaling regimes markedly different from those assumed in neural ODE literature. Depending on certain features of the network architecture, such as the smoothness of the activation function, one may obtain an alternative ODE limit, a stochastic differential equation or neither of these. These findings cast doubts on the validity of the neural ODE model as an adequate asymptotic description of deep ResNets and point to an alternative class of differential equations as a better description of the deep network limit.
Attention Model has now become an important concept in neural networks that has been researched within diverse application domains. This survey provides a structured and comprehensive overview of the developments in modeling attention. In particular, we propose a taxonomy which groups existing techniques into coherent categories. We review salient neural architectures in which attention has been incorporated, and discuss applications in which modeling attention has shown a significant impact. Finally, we also describe how attention has been used to improve the interpretability of neural networks. We hope this survey will provide a succinct introduction to attention models and guide practitioners while developing approaches for their applications.
Graph neural networks (GNNs) are a popular class of machine learning models whose major advantage is their ability to incorporate a sparse and discrete dependency structure between data points. Unfortunately, GNNs can only be used when such a graph-structure is available. In practice, however, real-world graphs are often noisy and incomplete or might not be available at all. With this work, we propose to jointly learn the graph structure and the parameters of graph convolutional networks (GCNs) by approximately solving a bilevel program that learns a discrete probability distribution on the edges of the graph. This allows one to apply GCNs not only in scenarios where the given graph is incomplete or corrupted but also in those where a graph is not available. We conduct a series of experiments that analyze the behavior of the proposed method and demonstrate that it outperforms related methods by a significant margin.
Deep learning has yielded state-of-the-art performance on many natural language processing tasks including named entity recognition (NER). However, this typically requires large amounts of labeled data. In this work, we demonstrate that the amount of labeled training data can be drastically reduced when deep learning is combined with active learning. While active learning is sample-efficient, it can be computationally expensive since it requires iterative retraining. To speed this up, we introduce a lightweight architecture for NER, viz., the CNN-CNN-LSTM model consisting of convolutional character and word encoders and a long short term memory (LSTM) tag decoder. The model achieves nearly state-of-the-art performance on standard datasets for the task while being computationally much more efficient than best performing models. We carry out incremental active learning, during the training process, and are able to nearly match state-of-the-art performance with just 25\% of the original training data.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191