Related papers: Linq-Embed-Mistral Technical Report
State-of-the-art retrieval models typically address a straightforward search scenario, in which retrieval tasks are fixed (e.g., finding a passage to answer a specific question) and only a single modality is supported for both queries and…
In this paper, we introduce ReasonEmbed, a novel text embedding model developed for reasoning-intensive document retrieval. Our work includes three key technical contributions. First, we propose ReMixer, a new data synthesis method that…
Ranking models play a crucial role in enhancing overall accuracy of text retrieval systems. These multi-stage systems typically utilize either dense embedding models or sparse lexical indices to retrieve relevant passages based on a given…
This report presents a unified instruction-based framework for learning generalized text embeddings optimized for both information retrieval (IR) and non-IR tasks. Built upon a decoder-only large language model (Mistral-7B), our approach…
The rapid expansion of multimedia content has made accurately retrieving relevant videos from large collections increasingly challenging. Recent advancements in text-video retrieval have focused on cross-modal interactions, large-scale…
We present QZhou-Embedding, a general-purpose contextual text embedding model with exceptional text representation capabilities. Built upon the Qwen2.5-7B-Instruct foundation model, we designed a unified multi-task framework comprising…
The relentless pursuit of enhancing Large Language Models (LLMs) has led to the advent of Super Retrieval-Augmented Generation (Super RAGs), a novel approach designed to elevate the performance of LLMs by integrating external knowledge…
Text embedding methods have become increasingly popular in both industrial and academic fields due to their critical role in a variety of natural language processing tasks. The significance of universal text embeddings has been further…
Embedding models are crucial for various natural language processing tasks but can be limited by factors such as limited vocabulary, lack of context, and grammatical errors. This paper proposes a novel approach to improve embedding…
The rapid advancement of Multimodal Large Language Models (MLLMs) has extended CLIP-based frameworks to produce powerful, universal embeddings for retrieval tasks. However, existing methods primarily focus on natural images, offering…
This paper presents the training methodology of Arctic-Embed 2.0, a set of open-source text embedding models built for accurate and efficient multilingual retrieval. While prior works have suffered from degraded English retrieval quality,…
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…
LLMs confront inherent limitations in terms of its knowledge, memory, and action. The retrieval augmentation stands as a vital mechanism to address these limitations, which brings in useful information from external sources to augment the…
Text embedding models serve as a fundamental component in real-world search applications. By mapping queries and documents into a shared embedding space, they deliver competitive retrieval performance with high efficiency. However, their…
We explore the effectiveness of an LLM-guided query refinement paradigm for extending the usability of embedding models to challenging zero-shot search and classification tasks. Our approach refines the embedding representation of a user…
Recent advancements in large language models (LLMs) integrated with external tools and APIs have successfully addressed complex tasks by using in-context learning or fine-tuning. Despite this progress, the vast scale of tool retrieval…
Retrieval augmentation has become an effective solution to empower large language models (LLMs) with external and verified knowledge sources from the database, which overcomes the limitations and hallucinations of LLMs in handling…
Existing retrieval benchmarks primarily consist of information-seeking queries (e.g., aggregated questions from search engines) where keyword or semantic-based retrieval is usually sufficient. However, many complex real-world queries…
Recently embedding-based retrieval or dense retrieval have shown state of the art results, compared with traditional sparse or bag-of-words based approaches. This paper introduces a model-agnostic doc-level embedding framework through large…
Traditional text embedding benchmarks primarily evaluate embedding models' capabilities to capture semantic similarity. However, more advanced NLP tasks require a deeper understanding of text, such as safety and factuality. These tasks…