Related papers: A Neural Network Solves, Explains, and Generates U…
Creating learning models that can exhibit sophisticated reasoning skills is one of the greatest challenges in deep learning research, and mathematics is rapidly becoming one of the target domains for assessing scientific progress in this…
Recent progress in large language models (LLMs) like GPT-4 and PaLM-2 has brought significant advancements in addressing math reasoning problems. In particular, OpenAI's latest version of GPT-4, known as GPT-4 Code Interpreter, shows…
Large pretrained language models (LMs) like BERT have improved performance in many disparate natural language processing (NLP) tasks. However, fine tuning such models requires a large number of training examples for each target task.…
Mathematical reasoning is an important research direction in the field of artificial intelligence. This article proposes a novel multi tool application framework for mathematical reasoning, aiming to achieve more comprehensive and accurate…
Neural-based end-to-end approaches to natural language generation (NLG) from structured data or knowledge are data-hungry, making their adoption for real-world applications difficult with limited data. In this work, we propose the new task…
Bug fixing is generally a manually-intensive task. However, recent work has proposed the idea of automated program repair, which aims to repair (at least a subset of) bugs in different ways such as code mutation, etc. Following in the same…
Current approaches to program synthesis with Large Language Models (LLMs) exhibit a "near miss syndrome": they tend to generate programs that semantically resemble the correct answer (as measured by text similarity metrics or human…
Automatic short answer grading is an important research direction in the exploration of how to use artificial intelligence (AI)-based tools to improve education. Current state-of-the-art approaches use neural language models to create…
Recently, neural networks have spread into numerous fields including many safety-critical systems. Neural networks are built (and trained) by programming in frameworks such as TensorFlow and PyTorch. Developers apply a rich set of…
Language models have demonstrated remarkable performance in solving reasoning tasks; however, even the strongest models still occasionally make reasoning mistakes. Recently, there has been active research aimed at improving reasoning…
Guiding large language models with a selected set of human-authored demonstrations is a common practice for improving LLM applications. However, human effort can be costly, especially in specialized domains (e.g., clinical diagnosis), and…
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…
Recent work has demonstrated substantial gains on many NLP tasks and benchmarks by pre-training on a large corpus of text followed by fine-tuning on a specific task. While typically task-agnostic in architecture, this method still requires…
Pre-trained models have been shown effective in many code intelligence tasks. These models are pre-trained on large-scale unlabeled corpus and then fine-tuned in downstream tasks. However, as the inputs to pre-training and downstream tasks…
We curate a comprehensive dataset of 4,550 questions and solutions from problem sets, midterm exams, and final exams across all MIT Mathematics and Electrical Engineering and Computer Science (EECS) courses required for obtaining a degree.…
Automated Program Repair (APR) aims to automatically fix bugs in the source code. Recently, as advances in Deep Learning (DL) field, there is a rise of Neural Program Repair (NPR) studies, which formulate APR as a translation task from…
Logic-based problems such as planning, theorem proving, or puzzles, typically involve combinatoric search and structured knowledge representation. Artificial neural networks are very successful statistical learners, however, for many years,…
Neural network-based methods represent the state-of-the-art in question generation from text. Existing work focuses on generating only questions from text without concerning itself with answer generation. Moreover, our analysis shows that…
Large language models (LLMs) have exhibited great potential in mathematical reasoning. However, there remains a performance gap in this area between existing open-source models and closed-source models such as GPT-4. In this paper, we…
Most state-of-the-art speech systems are using Deep Neural Networks (DNNs). Those systems require a large amount of data to be learned. Hence, learning state-of-the-art frameworks on under-resourced speech languages/problems is a difficult…