相关论文: Less is Enough: Synthesizing Diverse Data in LLM F…

We introduce Syntax-Aware Fill-In-the-Middle (SAFIM), a new benchmark for evaluating Large Language Models (LLMs) on the code Fill-in-the-Middle (FIM) task. This benchmark focuses on syntax-aware completions of program structures such as…

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…

When developing text classification models for real world applications, one major challenge is the difficulty to collect sufficient data for all text classes. In this work, we address this challenge by utilizing large language models (LLMs)…

Counterfactual explanations (CFEs) provide human-centric interpretability by identifying the minimal, actionable changes required to alter a machine learning model's prediction. Therefore, CFs can be used as (i) interventions for…

Large Multimodal Models (LMMs), or Vision-Language Models (VLMs), have shown impressive capabilities in a wide range of visual tasks. However, they often struggle with fine-grained visual reasoning, failing to identify domain-specific…

Generative data augmentation with latent diffusion models is a promising strategy for addressing class imbalance in medical imaging, yet current approaches focus on perceptual fidelity and domain-specific autoencoder fine-tuning while…

Large Language Models (LLMs) have impressive multilingual capabilities, but they suffer from unexpected code-switching, also known as language mixing, which involves switching to unexpected languages in the model response. This problem…

Despite increasing focus on data publication and discovery in materials science and related fields, the global view of materials data is highly sparse. This sparsity encourages training models on the union of multiple datasets, but simple…

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…

The Bayesian approach to feature extraction, known as factor analysis (FA), has been widely studied in machine learning to obtain a latent representation of the data. An adequate selection of the probabilities and priors of these bayesian…

Existing deep learning approaches leave out the semantic cues that are crucial in semantic segmentation present in complex scenarios including cluttered backgrounds and translucent objects, etc. To handle these challenges, we propose a…

Latent representations are critical for the performance and robustness of machine learning models, as they encode the essential features of data in a compact and informative manner. However, in vision tasks, these representations are often…

The effectiveness of machine learning models, particularly in unbalanced classification tasks, is often hindered by the failure to differentiate between critical instances near the decision boundary and redundant samples concentrated in the…

Large Language Models (LLMs) achieve strong linguistic performance, yet their internal mechanisms for producing these predictions remain unclear. We investigate the hypothesis that LLMs encode representations of linguistic constraint…

Despite large language models (LLMs) have achieved impressive achievements across numerous tasks, supervised fine-tuning (SFT) remains essential for adapting these models to specialized domains. However, SFT for domain specialization can be…

The scarcity of data in various scenarios, such as medical, industry and autonomous driving, leads to model overfitting and dataset imbalance, thus hindering effective detection and segmentation performance. Existing studies employ the…

Multimodal Large Language Models (MLLMs) have demonstrated outstanding performance across a variety of domains. However, training MLLMs is often inefficient, as much of the computation is redundant due to the long input sequences from…

Meta-learning offers a promising avenue for few-shot learning (FSL), enabling models to glean a generalizable feature embedding through episodic training on synthetic FSL tasks in a source domain. Yet, in practical scenarios where the…

Generative models have achieved remarkable progress with the emergence of flow matching (FM). It has demonstrated strong generative capabilities and attracted significant attention as a simulation-free flow-based framework capable of…

Synthetic text generated by Large Language Models (LLMs) is increasingly used for further training and improvement of LLMs. Diversity is crucial for the effectiveness of synthetic data, and researchers rely on prompt engineering to improve…