Related papers: Do Syntactic Categories Help in Developmentally Mo…
Curriculum Learning (CL) is a meta-learning paradigm that trains a model by feeding the data instances incrementally according to a schedule, which is based on difficulty progression. Defining meaningful difficulty assessment measures is…
Large Language Models (LLMs) are commonly pretrained on vast corpora of text without utilizing contextual metadata such as source, quality, or topic, leading to a context-free learning paradigm. While recent studies suggest that adding…
In-Context Learning (ICL) enables transformer-based language models to adapt to new tasks by conditioning on demonstration examples. However, traditional example-driven in-context learning lacks explicit modules for knowledge retrieval and…
With recent advances in large language models (LLMs), the concept of automatically generating children's educational materials has become increasingly realistic. Working toward the goal of age-appropriate simplicity in generated educational…
Code data has been shown to enhance the reasoning capabilities of large language models (LLMs), but it remains unclear which aspects of code are most responsible. We investigate this question with a systematic, data-centric framework. We…
Recent advancements in data-to-text generation largely take on the form of neural end-to-end systems. Efforts have been dedicated to improving text generation systems by changing the order of training samples in a process known as…
Current state-of-the-art NLP systems use large neural networks that require lots of computational resources for training. Inspired by human knowledge acquisition, researchers have proposed curriculum learning, - sequencing of tasks…
The in-context learning ability of large language models (LLMs) enables them to generalize to novel downstream tasks with relatively few labeled examples. However, they require enormous computational resources to be deployed. Alternatively,…
Representational spaces learned via language modeling are fundamental to Natural Language Processing (NLP), however there has been limited understanding regarding how and when during training various types of linguistic information emerge…
Curriculum learning in reinforcement learning is used to shape exploration by presenting the agent with increasingly complex tasks. The idea of curriculum learning has been largely applied in both animal training and pedagogy. In…
With the help of in-context learning (ICL), large language models (LLMs) have achieved impressive performance across various tasks. However, the function of descriptive instructions during ICL remains under-explored. In this work, we…
We introduce quantitative metrics for child language acquisition to evaluate language models. Our focus is on the formal syntactic and functional discourse properties of determiners in English, which young children acquire early and…
Multimodal models, such as the Contrastive Language-Image Pre-training (CLIP) model, have demonstrated remarkable success in aligning visual and linguistic representations. However, these models exhibit limitations when applied to…
Curriculum learning (CL) structures training from simple to complex samples, facilitating progressive learning. However, existing CL approaches for emotion recognition often rely on heuristic, data-driven, or model-based definitions of…
Recent advances in foundation models present new opportunities for interpretable visual recognition -- one can first query Large Language Models (LLMs) to obtain a set of attributes that describe each class, then apply vision-language…
Through pretraining on a corpus with various sources, Large Language Models (LLMs) have gained impressive performance. However, the impact of each component of the pretraining corpus remains opaque. As a result, the organization of the…
This work explores the degree to which grammar acquisition is driven by language `simplicity' and the source modality (speech vs. text) of data. Using BabyBERTa as a probe, we find that grammar acquisition is largely driven by exposure to…
Though linguistic knowledge emerges during large-scale language model pretraining, recent work attempt to explicitly incorporate human-defined linguistic priors into task-specific fine-tuning. Infusing language models with syntactic or…
Curriculum learning (CL) describes a machine learning training strategy in which samples are gradually introduced into the training process based on their difficulty. Despite a partially contradictory body of evidence in the literature, CL…
Many studies have evaluated the cognitive alignment of Pre-trained Language Models (PLMs), i.e., their correspondence to adult performance across a range of cognitive domains. Recently, the focus has expanded to the developmental alignment…