Related papers: Turning Language Model Training from Black Box int…
Large pre-trained language models have recently been expanded and applied to programming language tasks with great success, often through further pre-training of a strictly-natural language model--where training sequences typically contain…
Identifying logical errors in complex, incomplete or even contradictory and overall heterogeneous data like students' experimentation protocols is challenging. Recognizing the limitations of current evaluation methods, we investigate the…
Adults vary greatly in how effectively they learn a new language, but the signals driving the learning processes and individual differences remain unclear. Over seven days, we tracked behavioral learning and collected fMRI data from 102…
At the current pace of technological advancements, Generative AI models, including both Large Language Models and Large Multi-modal Models, are becoming integral to the developer workspace. However, challenges emerge due to the 'black box'…
Transformer-based models are now predominant in NLP. They outperform approaches based on static models in many respects. This success has in turn prompted research that reveals a number of biases in the language models generated by…
Since high dropout rates in online learning platforms were reported, various factors affecting learner retention have been identified, with learners' perceptions of their experiences playing a crucial role in shaping their persistence. For…
Integrating free-text explanations to in-context learning of large language models (LLM) is shown to elicit strong reasoning capabilities along with reasonable explanations. In this paper, we consider the problem of leveraging the…
Transformer-based language models have achieved significant success; however, their internal mechanisms remain largely opaque due to the complexity of non-linear interactions and high-dimensional operations. While previous studies have…
Recent psycholinguistic studies have drawn conflicting conclusions about the relationship between the quality of a language model and the ability of its surprisal estimates to predict human reading times, which has been speculated to be due…
Large Language Models (LLMs) are increasingly deployed to automatically label and analyze educational dialogue at scale, yet current pipelines lack reliable ways to detect when models are wrong. We investigate whether reasoning generated by…
Background and Context: Large Language Models (LLMs) are more accessible and accurate than ever before, raising significant concerns for computing educators. One major concern is students using LLMs to bypass the effort needed to understand…
The deep learning architecture associated with ChatGPT and related generative AI products is known as transformers. Initially applied to Natural Language Processing, transformers and the self-attention mechanism they exploit have gained…
Distinguishing scripted from spontaneous speech is an essential tool for better understanding how speech styles influence speech processing research. It can also improve recommendation systems and discovery experiences for media users…
While artificial intelligence (AI) technology is becoming increasingly popular, its underlying mechanisms tend to remain opaque to most people. To address this gap, the field of AI literacy aims to develop various resources to teach people…
Generative artificial intelligence (GenAI) can reshape education and learning. While large language models (LLMs) like ChatGPT dominate current educational research, multimodal capabilities, such as text-to-speech and text-to-image, are…
Adapting one's thought process based on corrective feedback is an essential ability in human learning, particularly in collaborative settings. In contrast, the current large language model training paradigm relies heavily on modeling vast,…
Recent advances in vision-and-language modeling have seen the development of Transformer architectures that achieve remarkable performance on multimodal reasoning tasks. Yet, the exact capabilities of these black-box models are still poorly…
Recent work has demonstrated the promise of combining local explanations with active learning for understanding and supervising black-box models. Here we show that, under specific conditions, these algorithms may misrepresent the quality of…
Can language models (LMs) learn to faithfully describe their internal computations? Are they better able to describe themselves than other models? We study the extent to which LMs' privileged access to their own internals can be leveraged…
This paper focuses on AI tutors in foreign language learning, a field of application of AI tutors with great development, especially during the last years, when great advances in natural language understanding and processing in real time,…