Related papers: Layer-Aware Embedding Fusion for LLMs in Text Clas…

Large language models (LLMs) have demonstrated impressive capabilities across diverse languages. This study explores how LLMs handle multilingualism. Based on observed language ratio shifts among layers and the relationships between network…

Large language models (LLMs) excel at capturing semantic nuances and therefore show impressive relevance ranking performance in modern recommendation and search systems. However, they suffer from high computational overhead under industrial…

(Natural Language Processing) NLP techniques such as text classification and topic discovery are very useful in many application areas including information retrieval, knowledge discovery, policy formulation, and decision-making. However,…

Decoder-only LLM-based embedding models are beginning to outperform BERT or T5-based embedding models in general-purpose text embedding tasks, including dense vector-based retrieval. In this work, we introduce NV-Embed, incorporating…

Many vision-related tasks benefit from reasoning over multiple modalities to leverage complementary views of data in an attempt to learn robust embedding spaces. Most deep learning-based methods rely on a late fusion technique whereby…

Word embeddings are a powerful approach for analyzing language and have been widely popular in numerous tasks in information retrieval and text mining. Training embeddings over huge corpora is computationally expensive because the input is…

This paper presents an efficient decoding approach for end-to-end automatic speech recognition (E2E-ASR) with large language models (LLMs). Although shallow fusion is the most common approach to incorporate language models into E2E-ASR…

Multilingual Machine Translation promises to improve translation quality between non-English languages. This is advantageous for several reasons, namely lower latency (no need to translate twice), and reduced error cascades (e.g., avoiding…

Intelligently reasoning about the world often requires integrating data from multiple modalities, as any individual modality may contain unreliable or incomplete information. Prior work in multimodal learning fuses input modalities only…

Recent large language models (LLMs) have demonstrated exceptional performance on general-purpose text embedding tasks. While dense embeddings have dominated related research, we introduce the first lexicon-based embeddings (LENS) leveraging…

We propose a novel discriminative model that learns embeddings from multilingual and multi-modal data, meaning that our model can take advantage of images and descriptions in multiple languages to improve embedding quality. To that end, we…

The growing demand for large language models (LLMs) with tunable reasoning capabilities in many real-world applications highlights a critical need for methods that can efficiently produce a spectrum of models balancing reasoning depth and…

License Plate Recognition (LPR) plays a critical role in various applications, such as toll collection, parking management, and traffic law enforcement. Although LPR has witnessed significant advancements through the development of deep…

Recently, FuseLLM introduced the concept of knowledge fusion to transfer the collective knowledge of multiple structurally varied LLMs into a target LLM through lightweight continual training. In this report, we extend the scalability and…

Recent studies in prompting large language model (LLM) for document-level machine translation (DMT) primarily focus on the inter-sentence context by flatting the source document into a long sequence. This approach relies solely on the…

Embedding models are crucial to modern NLP. However, the creation of the most effective models relies on carefully constructed supervised finetuning data. For high resource languages, such as English, such datasets are readily available.…

Supervised fine-tuning (SFT) is crucial for adapting Large Language Models (LLMs) to specific tasks. In this work, we demonstrate that the order of training data can lead to significant training imbalances, potentially resulting in…

Text embeddings from Large Language Models (LLMs) have become foundational for numerous applications. However, these models typically operate on raw text, overlooking the rich structural information, such as hyperlinks or citations, that…

Entity matching (EM) is a critical step in entity resolution (ER). Recently, entity matching based on large language models (LLMs) has shown great promise. However, current LLM-based entity matching approaches typically follow a binary…

Large language models (LLMs) have shown an impressive ability to perform tasks believed to require thought processes. When the model does not document an explicit thought process, it becomes difficult to understand the processes occurring…