Related papers: Finetuning Transformer Models to Build ASAG System

In this work, we introduce a simple yet efficient post-processing model for automatic speech recognition (ASR). Our model has Transformer-based encoder-decoder architecture which "translates" ASR model output into grammatically and…

Reward modeling is essential for aligning large language models with human preferences through reinforcement learning. To provide accurate reward signals, a reward model (RM) should stimulate deep thinking and conduct interpretable…

In this work, we evaluate 10 open-source instructed LLMs on four representative code comprehension and generation tasks. We have the following main findings. First, for the zero-shot setting, instructed LLMs are very competitive on code…

Although large language models (LLMs) have achieved remarkable performance across various tasks, they remain prone to errors. A key challenge is enabling them to self-correct. While prior research has relied on external tools or large…

Today, most large-scale conversational AI agents (e.g. Alexa, Siri, or Google Assistant) are built using manually annotated data to train the different components of the system. Typically, the accuracy of the ML models in these components…

Fine-tuning large language models (LLMs) has achieved remarkable performance across various natural language processing tasks, yet it demands more and more memory as model sizes keep growing. To address this issue, the recently proposed…

The choice of input-data used to train algorithm-selection models is recognised as being a critical part of the model success. Recently, feature-free methods for algorithm-selection that use short trajectories obtained from running a solver…

Stochastic variance-reduced algorithms such as Stochastic Average Gradient (SAG) and SAGA, and their deterministic counterparts like the Incremental Aggregated Gradient (IAG) method, have been extensively studied in large-scale machine…

Scaling test-time compute brings substantial performance gains for large language models (LLMs). By sampling multiple answers and heuristically aggregate their answers (e.g., either through majority voting or using verifiers to rank the…

Large Language Models (LLMs) are increasingly explored for educational tasks such as grading, yet their alignment with human evaluation in real classrooms remains underexamined. In this study, we investigate the feasibility of using an LLM…

In education, the traditional Automatic Short Answer Grading (ASAG) with feedback problem has focused primarily on evaluating text-only responses. However, real-world assessments often include multimodal responses containing both diagrams…

High-quality computer science education is limited by the difficulty of providing instructor feedback to students at scale. While this feedback could in principle be automated, supervised approaches to predicting the correct feedback are…

Large Transformer-based language models are pre-trained on corpora of varying sizes, for a different number of steps and with different batch sizes. At the same time, more fundamental components, such as the pre-training objective or…

Residual stresses, which remain within a component after processing, can deteriorate performance. Accurately determining their full-field distributions is essential for optimizing the structural integrity and longevity. However, the…

The class of autoregressive (AR) processes is extensively used to model temporal dependence in observed time series. Such models are easily available and routinely fitted using freely available statistical software like R. A potential…

We present an algorithm for supervised learning using tensor networks, employing a step of preprocessing the data by coarse-graining through a sequence of wavelet transformations. We represent these transformations as a set of tensor…

Fully finetuning foundation language models (LMs) with billions of parameters is often impractical due to high computational costs, memory requirements, and the risk of overfitting. Although methods like low-rank adapters help address these…

Recently, generative pre-training based models have demonstrated remarkable results on Aspect-based Sentiment Analysis (ABSA) task. However, previous works overemphasize crafting various templates to paraphrase training targets for enhanced…

Large Language Models (LLMs), with billions of parameters, present significant challenges for full finetuning due to the high computational demands, memory requirements, and impracticality of many real-world applications. When faced with…

Several useful variance-reduced stochastic gradient algorithms, such as SVRG, SAGA, Finito, and SAG, have been proposed to minimize empirical risks with linear convergence properties to the exact minimizer. The existing convergence results…