Related papers: A Neural Network Solves, Explains, and Generates U…

We present a new method for scaling automatic configuration of computer networks. The key idea is to relax the computationally hard search problem of finding a configuration that satisfies a given specification into an approximate objective…

This study highlights the potential of fine-tuned ChatGPT (GPT-3.5) for automatically scoring student written constructed responses using example assessment tasks in science education. Recent studies on OpenAI's generative model GPT-3.5…

Computing students increasingly rely on generative AI tools for programming assistance, often without formal instruction or guidance. This highlights a need to teach students how to effectively interact with AI models, particularly through…

Recent years have seen the proposal of a number of neural architectures for the problem of Program Induction. Given a set of input-output examples, these architectures are able to learn mappings that generalize to new test inputs. While…

Recurrent neural networks (RNNs) have reached striking performance in many natural language processing tasks. This has renewed interest in whether these generic sequence processing devices are inducing genuine linguistic knowledge. Nearly…

Current machine learning has made great progress on computer vision and many other fields attributed to the large amount of high-quality training samples, while it does not work very well on genomic data analysis, since they are notoriously…

Mathematical reasoning is an important capability of large language models~(LLMs) for real-world applications. To enhance this capability, existing work either collects large-scale math-related texts for pre-training, or relies on stronger…

Advances in deep learning have resulted in state-of-the-art performance for many audio classification tasks but, unlike humans, these systems traditionally require large amounts of data to make accurate predictions. Not every person or…

Solving mathematical problems requires advanced reasoning abilities and presents notable challenges for large language models. Previous works usually synthesize data from proprietary models to augment existing datasets, followed by…

We use the EMNIST dataset of handwritten digits to test a simple approach for few-shot learning. A fully connected neural network is pre-trained with a subset of the 10 digits and used for few-shot learning with untrained digits. Two basic…

The advent of instruction-tuned language models that convincingly mimic human writing poses a significant risk of abuse. However, such abuse may be counteracted with the ability to detect whether a piece of text was composed by a language…

Autoregressive language models, pretrained using large text corpora to do well on next word prediction, have been successful at solving many downstream tasks, even with zero-shot usage. However, there is little theoretical understanding of…

Digital technologies are increasingly used in education to reduce the workload of teachers and students. However, creating open-ended study or examination questions and grading their answers is still a tedious task. This thesis presents the…

There is increasing interest in employing large language models (LLMs) as cognitive models. For such purposes, it is central to understand which properties of human cognition are well-modeled by LLMs, and which are not. In this work, we…

In this paper, we present a novel nonlinear programming-based approach to fine-tune pre-trained neural networks to improve robustness against adversarial attacks while maintaining high accuracy on clean data. Our method introduces…

Deep learning, a branch of artificial intelligence, is a data-driven method that uses multiple layers of interconnected units or neurons to learn intricate patterns and representations directly from raw input data. Empowered by this…

Answering compositional questions that require multiple steps of reasoning against text is challenging, especially when they involve discrete, symbolic operations. Neural module networks (NMNs) learn to parse such questions as executable…

Just like other few-shot learning problems, few-shot segmentation aims to minimize the need for manual annotation, which is particularly costly in segmentation tasks. Even though the few-shot setting reduces this cost for novel test…

When neural networks are used to solve differential equations, they usually produce solutions in the form of black-box functions that are not directly mathematically interpretable. We introduce a method for generating symbolic expressions…

Recent advances in few-shot question answering (QA) mostly rely on the power of pre-trained large language models (LLMs) and fine-tuning in specific settings. Although the pre-training stage has already equipped LLMs with powerful reasoning…