Related papers: Can Language Models Employ the Socratic Method? Ex…

Large pre-trained language models such as GPT-3, Codex, and Google's language model are now capable of generating code from natural language specifications of programmer intent. We view these developments with a mixture of optimism and…

We propose TuringAdvice, a new challenge task and dataset for language understanding models. Given a written situation that a real person is currently facing, a model must generate helpful advice in natural language. Our evaluation…

In this thesis, we address the data scarcity and limitations of linguistic theory by proposing language-agnostic multi-task training methods. First, we introduce a meta-learning-based approach, meta-transfer learning, in which information…

Meta-learning and few-shot prompting are viable methods to induce certain types of compositional behaviour. However, these methods can be very sensitive to the choice of support examples used. Choosing good supports from the training data…

Second language acquisition (SLA) modeling is to predict whether second language learners could correctly answer the questions according to what they have learned. It is a fundamental building block of the personalized learning system and…

In the realm of natural language processing, the understanding of tabular data has perpetually stood as a focal point of scholarly inquiry. The emergence of expansive language models, exemplified by the likes of ChatGPT, has ushered in a…

Debugging is a vital but challenging skill for beginner programmers to learn. It is also a difficult skill to teach. For secondary school teachers, who may lack time or programming experience, honing students' understanding of debugging can…

Existing math datasets evaluate the reasoning abilities of large language models (LLMs) by either using the final answer or the intermediate reasoning steps derived from static examples. However, the former approach fails to surface model's…

The computing education community has a rich history of pedagogical innovation designed to support students in introductory courses, and to support teachers in facilitating student learning. Very recent advances in artificial intelligence…

When tasked with supporting multiple languages for a given problem, two approaches have arisen: training a model for each language with the annotation budget divided equally among them, and training on a high-resource language followed by…

Neural-symbolic methods have demonstrated efficiency in enhancing the reasoning abilities of large language models (LLMs). However, existing methods mainly rely on syntactically mapping natural languages to complete formal languages like…

Can large language models improve without external data -- by generating their own questions and answers? We hypothesize that a pre-trained language model can improve its reasoning skills given only a single prompt specifying the topic…

Providing consistent, individualized feedback to teachers on their instruction can improve student learning outcomes. Such feedback can especially benefit novice instructors who teach on online platforms and have limited access to…

Autonomous agents are able to draw on a wide variety of potential sources of task knowledge; however current approaches invariably focus on only one or two. Here we investigate the challenges and impact of exploiting diverse knowledge…

Teacher education requires deliberate practice with learners who exhibit identifiable strengths, weaknesses, and partial mastery. Large language models could support such practice by simulating students with known skill components, enabling…

We study the problem of leveraging the syntactic structure of text to enhance pre-trained models such as BERT and RoBERTa. Existing methods utilize syntax of text either in the pre-training stage or in the fine-tuning stage, so that they…

Probing is a popular method to discern what linguistic information is contained in the representations of pre-trained language models. However, the mechanism of selecting the probe model has recently been subject to intense debate, as it is…

The ability to combine linguistic guidance from others with direct experience is central to human development, enabling safe and rapid learning in new environments. How do people integrate these two sources of knowledge, and how might AI…

Large language models make remarkable progress in reasoning capabilities. Existing works focus mainly on deductive reasoning tasks (e.g., code and math), while another type of reasoning mode that better aligns with human learning, inductive…

In programming education, Debugging and Teaching (DT) task is a common scenario where students receive assistance in correcting their erroneous code. The task involves multiple inputs, including erroneous code, error messages, reference…