Related papers: LEMUR: Learned Multi-Vector Retrieval
We introduce CEMTM, a context-enhanced multimodal topic model designed to infer coherent and interpretable topic structures from both short and long documents containing text and images. CEMTM builds on fine-tuned large vision language…
In modern e-commerce search systems, dense retrieval has become an indispensable component. By computing similarities between query and item (product) embeddings, it efficiently selects candidate products from large-scale repositories. With…
Large multimodal models (LMMs) have achieved high performance in vision-language tasks involving single image but they struggle when presented with a collection of multiple images (Multiple Image Question Answering scenario). These tasks,…
Providing access to information across languages has been a goal of Information Retrieval (IR) for decades. While progress has been made on Cross Language IR (CLIR) where queries are expressed in one language and documents in another, the…
Multimodal retrieval methods have limitations in handling complex, compositional queries that require reasoning about the visual content of both the query and the retrieved entities. On the other hand, Large Multimodal Models (LMMs) can…
Recent work has demonstrated that vector offsets obtained by subtracting pretrained word embedding vectors can be used to predict lexical relations with surprising accuracy. Inspired by this finding, in this paper, we extend the idea to the…
Recent work (Weller et al., 2025) introduced a naturalistic dataset called LIMIT and showed empirically that a wide range of popular single-vector embedding models suffer substantial drops in retrieval quality, raising concerns about the…
Vector representations and vector space modeling (VSM) play a central role in modern machine learning. We propose a novel approach to `vector similarity searching' over dense semantic representations of words and documents that can be…
Representation learning of knowledge graphs aims to embed entities and relations into low-dimensional vectors. Most existing works only consider the direct relations or paths between an entity pair. It is considered that such approaches…
We introduce MRMR, the first expert-level multidisciplinary multimodal retrieval benchmark requiring intensive reasoning. MRMR contains 1,502 queries spanning 23 domains, with positive documents carefully verified by human experts. Compared…
We propose the Neural Vector Space Model (NVSM), a method that learns representations of documents in an unsupervised manner for news article retrieval. In the NVSM paradigm, we learn low-dimensional representations of words and documents…
Recent advancements in large language models (LLMs) have driven interest in billion-scale retrieval models with strong generalization across retrieval tasks and languages. Additionally, progress in large vision-language models has created…
Vector embeddings derived from large language models (LLMs) show promise in capturing latent information from the literature. Interestingly, these can be integrated into material embeddings, potentially useful for data-driven predictions of…
Retrieval-augmented large language models (LLMs) leverage relevant content retrieved by information retrieval systems to generate correct responses, aiming to alleviate the hallucination problem. However, existing retriever-responder…
Semantic retrieval, which retrieves semantically matched items given a textual query, has been an essential component to enhance system effectiveness in e-commerce search. In this paper, we study the multimodal retrieval problem, where the…
Document-level Relation Extraction (DocRE) involves identifying relations between entities across multiple sentences in a document. Evidence sentences, crucial for precise entity pair relationships identification, enhance focus on essential…
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…
Language model (LM) pretraining can learn various knowledge from text corpora, helping downstream tasks. However, existing methods such as BERT model a single document, and do not capture dependencies or knowledge that span across…
Cross-modal retrieval across image and text modalities is a challenging task due to its inherent ambiguity: An image often exhibits various situations, and a caption can be coupled with diverse images. Set-based embedding has been studied…
Large Language Models (LLMs) have been shown to enhance the effectiveness of enriching item descriptions, thereby improving the accuracy of recommendation systems. However, most existing approaches either rely on text-only prompting or…