Related papers: Enhancing Retrieval Performance: An Ensemble Appro…

With the growing popularity of RAG, the capabilities of embedding models are gaining increasing attention. Embedding models are primarily trained through contrastive loss learning, with negative examples being a key component. Previous work…

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…

Large language model (LLM) based listwise reranking has emerged as the dominant paradigm for achieving state-of-the-art ranking effectiveness in information retrieval. However, its reliance on feeding full passage texts into the LLM…

Text retrieval plays a crucial role in incorporating factual knowledge for decision making into language processing pipelines, ranging from chat-based web search to question answering systems. Current state-of-the-art text retrieval models…

E-commerce search engines often rely solely on product titles as input for ranking models with latency constraints. However, this approach can result in suboptimal relevance predictions, as product titles often lack sufficient detail to…

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…

Pairwise re-ranking models predict which of two documents is more relevant to a query and then aggregate a final ranking from such preferences. This is often more effective than pointwise re-ranking models that directly predict a relevance…

Web-scale search systems typically tackle the scalability challenge with a two-step paradigm: retrieval and ranking. The retrieval step, also known as candidate selection, often involves extracting standardized entities, creating an…

Ranking a set of items based on their relevance to a given query is a core problem in search and recommendation. Transformer-based ranking models are the state-of-the-art approaches for such tasks, but they score each query-item…

Advanced relevance models, such as those that use large language models (LLMs), provide highly accurate relevance estimations. However, their computational costs make them infeasible for processing large document corpora. To address this,…

Discovering relevant patterns for a particular user remains a challenging tasks in data mining. Several approaches have been proposed to learn user-specific pattern ranking functions. These approaches generalize well, but at the expense of…

In this paper we explore the effects of negative sampling in dual encoder models used to retrieve passages for automatic question answering. We explore four negative sampling strategies that complement the straightforward random sampling of…

Entity Linking has two main open areas of research: 1) generate candidate entities without using alias tables and 2) generate more contextual representations for both mentions and entities. Recently, a solution has been proposed for the…

Existing multilingual embedding models often encounter challenges in cross-lingual scenarios due to imbalanced linguistic resources and less consideration of cross-lingual alignment during training. Although standardized contrastive…

Modern knowledge-intensive systems, such as retrieval-augmented generation (RAG), rely on effective retrievers to establish the performance ceiling for downstream modules. However, retriever training has been bottlenecked by sparse,…

Despite the recent advancement in Retrieval-Augmented Generation (RAG) systems, most retrieval methodologies are often developed for factual retrieval, which assumes query and positive documents are semantically similar. In this paper, we…

Most successful information extraction systems operate with access to a large collection of documents. In this work, we explore the task of acquiring and incorporating external evidence to improve extraction accuracy in domains where the…

Reranking is fundamental to information retrieval and retrieval-augmented generation, with recent Large Language Models (LLMs) significantly advancing reranking quality. Most current works rely on large-scale LLMs (>7B parameters),…

Rerankers, typically cross-encoders, are computationally intensive but are frequently used because they are widely assumed to outperform cheaper initial IR systems. We challenge this assumption by measuring reranker performance for full…

Despite the advantages of their low-resource settings, traditional sparse retrievers depend on exact matching approaches between high-dimensional bag-of-words (BoW) representations of both the queries and the collection. As a result,…