Related papers: Arctic-Embed: Scalable, Efficient, and Accurate Te…

In this report, we introduce pplx-embed, a family of multilingual embedding models that employ multi-stage contrastive learning on a diffusion-pretrained language model backbone for web-scale retrieval. By leveraging bidirectional attention…

Recent information retrieval (IR) models are pre-trained and instruction-tuned on massive datasets and tasks, enabling them to perform well on a wide range of tasks and potentially generalize to unseen tasks with instructions. However,…

Text classification is one of the most frequent tasks for processing textual data, facilitating among others research from large-scale datasets. Embeddings of different kinds have recently become the de facto standard as features used for…

We present SwiftEmbed, a production-oriented serving system for static token embeddings that achieves 1.12\,ms p50 latency for single-text requests while maintaining a 60.6 MTEB average score across 8 representative tasks. Built around the…

Multimodal chest X-Ray analysis often fine-tunes large vision-language models, which is computationally costly. We study parameter-efficient training (PET) strategies, including frozen encoders, BitFit, LoRA, and adapters for multi-label…

Large language models (LLMs) with decoder-only architectures demonstrate remarkable in-context learning (ICL) capabilities. This feature enables them to effectively handle both familiar and novel tasks by utilizing examples provided within…

In Retrieval-Augmented Generation (RAG) tasks using Large Language Models (LLMs), the quality of retrieved information is critical to the final output. This paper introduces the IRSC benchmark for evaluating the performance of embedding…

Over the past decade, recommender systems have experienced a surge in popularity. Despite notable progress, they grapple with challenging issues, such as high data dimensionality and sparseness. Representing users and items as…

Extracting top-k keywords and documents using weighting schemes are popular techniques employed in text mining and machine learning for different analysis and retrieval tasks. The weights are usually computed in the data preprocessing step,…

Current sentence embedding evaluations typically rely on static test beds like the Massive Text Embedding Benchmark (MTEB). While invaluable, repeated tuning on a fixed suite can inflate reported scores and obscure real-world robustness. We…

Given multiple source word embeddings learnt using diverse algorithms and lexical resources, meta word embedding learning methods attempt to learn more accurate and wide-coverage word embeddings. Prior work on meta-embedding has repeatedly…

We present MetricBERT, a BERT-based model that learns to embed text under a well-defined similarity metric while simultaneously adhering to the ``traditional'' masked-language task. We focus on downstream tasks of learning similarities for…

Network embedding (or graph embedding) has been widely used in many real-world applications. However, existing methods mainly focus on networks with single-typed nodes/edges and cannot scale well to handle large networks. Many real-world…

Text-rich images, where text serves as the central visual element guiding the overall understanding, are prevalent in real-world applications, such as presentation slides, scanned documents, and webpage snapshots. Tasks involving multiple…

Developers prefer to utilize third-party libraries when they implement some functionalities and Application Programming Interfaces (APIs) are frequently used by them. Facing an unfamiliar API, developers tend to consult tutorials as…

Deep language models learning a hierarchical representation proved to be a powerful tool for natural language processing, text mining and information retrieval. However, representations that perform well for retrieval must capture semantic…

How much private information do text embeddings reveal about the original text? We investigate the problem of embedding \textit{inversion}, reconstructing the full text represented in dense text embeddings. We frame the problem as…

Training large text-to-image models requires high-quality, curated datasets with diverse content and detailed captions. Yet the cost and complexity of collecting, filtering, deduplicating, and re-captioning such corpora at scale hinders…

Pretrained contextualized embeddings are powerful word representations for structured prediction tasks. Recent work found that better word representations can be obtained by concatenating different types of embeddings. However, the…

Modern information retrieval (IR) models, trained exclusively on standard <query, passage> pairs, struggle to effectively interpret and follow explicit user instructions. We introduce InF-IR, a large-scale, high-quality training corpus…