Related papers: DADA: Dialect Adaptation via Dynamic Aggregation o…

Machine learning models often struggle to generalize across domains with varying data distributions, such as differing noise levels, leading to degraded performance. Traditional strategies like personalized training, which trains separate…

Multi-source unsupervised domain adaptation (MUDA) aims to transfer knowledge from related source domains to an unlabeled target domain. While recent MUDA methods have shown promising results, most focus on aligning the overall feature…

Text classification is a representative downstream task of natural language processing, and has exhibited excellent performance since the advent of pre-trained language models based on Transformer architecture. However, in pre-trained…

The increasing sizes of large language models (LLMs) result in significant computational overhead and memory usage when adapting these models to specific tasks or domains. Various parameter-efficient fine-tuning (PEFT) methods have been…

We introduce RE-Adapt, an approach to fine-tuning large language models on new domains without degrading any pre-existing instruction-tuning. We reverse engineer an adapter which isolates what an instruction-tuned model has learned beyond…

Traditional machine learning assumes that training and test sets are derived from the same distribution; however, this assumption does not always hold in practical applications. This distribution disparity can lead to severe performance…

Retrieval-Augmented Large Language Models (LLMs), which incorporate the non-parametric knowledge from external knowledge bases into LLMs, have emerged as a promising approach to enhancing response accuracy in several tasks, such as…

The development of state-of-the-art generative large language models (LLMs) disproportionately relies on English-centric tokenizers, vocabulary and pre-training data. Despite the fact that some LLMs have multilingual capabilities, recent…

Considering the challenges faced by large language models (LLMs) in logical reasoning and planning, prior efforts have sought to augment LLMs with access to external solvers. While progress has been made on simple reasoning problems,…

Pretrained language models (PLMs) perform poorly under adversarial attacks. To improve the adversarial robustness, adversarial data augmentation (ADA) has been widely adopted to cover more search space of adversarial attacks by adding…

Dialectal Arabic (DA) varieties are under-served by language technologies, particularly large language models (LLMs). This trend threatens to exacerbate existing social inequalities and limits LLM applications, yet the research community…

Domain adaptation (DA) is the task of classifying an unlabeled dataset (target) using a labeled dataset (source) from a related domain. The majority of successful DA methods try to directly match the distributions of the source and target…

Anomaly detection in complex industrial environments poses unique challenges, particularly in contexts characterized by data sparsity and evolving operational conditions. Predictive maintenance (PdM) in such settings demands methodologies…

Modern software systems generate extensive heterogeneous log data with dynamic formats, fragmented event sequences, and varying temporal patterns, making anomaly detection both crucial and challenging. To address these complexities, we…

Effectively integrating Large Language Models (LLMs) into autonomous driving requires a balance between leveraging high-level reasoning and maintaining real-time efficiency. Existing approaches either activate LLMs too frequently, causing…

Within the rapidly evolving domain of Electronic Design Automation (EDA), Large Language Models (LLMs) have emerged as transformative technologies, offering unprecedented capabilities for optimizing and automating various aspects of…

Ensembling different large language models (LLMs) to unleash their complementary potential and harness their individual strengths is highly valuable. Nevertheless, vocabulary discrepancies among various LLMs have constrained previous…

Labeled Latent Dirichlet Allocation (LLDA) is an extension of the standard unsupervised Latent Dirichlet Allocation (LDA) algorithm, to address multi-label learning tasks. Previous work has shown it to perform in par with other…

Data-driven based approaches, in spite of great success in many tasks, have poor generalization when applied to unseen image domains, and require expensive cost of annotation especially for dense pixel prediction tasks such as semantic…

Data augmentation (DA) has gained widespread popularity in deep speaker models due to its ease of implementation and significant effectiveness. It enriches training data by simulating real-life acoustic variations, enabling deep neural…