Related papers: Masked Language Modeling Becomes Conditional Densi…

Incorporating language-specific (LS) modules is a proven method to boost performance in multilingual machine translation. This approach bears similarity to Mixture-of-Experts (MoE) because it does not inflate FLOPs. However, the scalability…

In mathematical reasoning tasks, the advancement of Large Language Models (LLMs) relies heavily on high-quality training data with clearly defined and well-graded difficulty levels. However, existing data synthesis methods often suffer from…

Masked language modeling (MLM) has been widely used for pre-training effective bidirectional representations, but incurs substantial training costs. In this paper, we propose a novel concept-based curriculum masking (CCM) method to…

Vision Language Models (VLMs) often struggle with chart understanding tasks, particularly in accurate chart description and complex reasoning. Synthetic data generation is a promising solution, while usually facing the challenge of noise…

Transformer-based large language models (LLMs) are comprised of billions of parameters arranged in deep and wide computational graphs. Several studies on LLM efficiency optimization argue that it is possible to prune a significant portion…

Human Multimodal Language Understanding (MLU) aims to infer human intentions by integrating related cues from heterogeneous modalities. Existing works predominantly follow a ``learning to attend" paradigm, which maximizes mutual information…

Recent advances in text-to-image (T2I) generation have enabled visually coherent image synthesis from descriptions, but generating images containing multiple given subjects remains challenging. As the number of reference identities…

Recent advances in product bundling have leveraged multimodal information through sophisticated encoders, but remain constrained by limited semantic understanding and a narrow scope of knowledge. Therefore, some attempts employ In-context…

This paper explores the challenges of test-time scaling of large language models (LLMs), regarding both the data and inference efficiency. We highlight the diversity of multi-lingual reasoning based on our pilot studies, and then introduce…

We introduce a transformer-based morpheme segmentation system that augments a low-resource training signal through multitask learning and LLM-generated synthetic data. Our framework jointly predicts morphological segments and glosses from…

Large Language Models (LLMs) have emerged as powerful tools for generating data across various modalities. By transforming data from a scarce resource into a controllable asset, LLMs mitigate the bottlenecks imposed by the acquisition costs…

The paper presents an approach to semantic grounding of language models (LMs) that conceptualizes the LM as a conditional model generating text given a desired semantic message formalized as a set of entity-relationship triples. It embeds…

Structured Latent Attribute Models (SLAMs) are a family of discrete latent variable models widely used in education, psychology, and epidemiology to model multivariate categorical data. A SLAM assumes that multiple discrete latent…

This work delves into the expanding role of large language models (LLMs) in generating artificial data. LLMs are increasingly employed to create a variety of outputs, including annotations, preferences, instruction prompts, simulated…

The latent class model is a widely used mixture model for multivariate discrete data. Besides the existence of qualitatively heterogeneous latent classes, real data often exhibit additional quantitative heterogeneity nested within each…

In this paper we propose and study a technique to impose structural constraints on the output of a neural network, which can reduce amount of computation and number of parameters besides improving prediction accuracy when the output is…

Large language models (LLMs) achieve strong performance across diverse tasks, largely driven by high-quality web data used in pre-training. However, recent studies indicate this data source is rapidly depleting. Synthetic data emerges as a…

We present a comprehensive evaluation of structured decoding for text-to-table generation with large language models (LLMs). While previous work has primarily focused on unconstrained generation of tables, the impact of enforcing structural…

Synthetic data augmentation via large language models (LLMs) allows researchers to leverage additional training data, thus enhancing the performance of downstream tasks, especially when real-world data is scarce. However, the generated data…

Standard meta-learning for representation learning aims to find a common representation to be shared across multiple tasks. The effectiveness of these methods is often limited when the nuances of the tasks' distribution cannot be captured…