Related papers: DocRetriever: A Plug-and-Play Framework for Multim…

Comprehending long visual documents, where information is distributed across extensive pages of text and visual elements, is a critical but challenging task for modern Vision-Language Models (VLMs). Existing approaches falter on a…

In the real world, where information is abundant and diverse across different modalities, understanding and utilizing various data types to improve retrieval systems is a key focus of research. Multimodal composite retrieval integrates…

Current medical retrieval benchmarks primarily emphasize lexical or shallow semantic similarity, overlooking the reasoning-intensive demands that are central to clinical decision-making. In practice, physicians often retrieve authoritative…

Developing effective biomedical retrieval models is important for excelling at knowledge-intensive biomedical tasks but still challenging due to the deficiency of sufficient publicly annotated biomedical data and computational resources. We…

Recent progress in deep learning has continuously improved the accuracy of dialogue response selection. In particular, sophisticated neural network architectures are leveraged to capture the rich interactions between dialogue context and…

Code search has usually been evaluated as first-stage retrieval, even though production systems rely on broader pipelines with reranking and developer-style queries. Existing benchmarks also suffer from data contamination, label noise, and…

Sparse document representations have been widely used to retrieve relevant documents via exact lexical matching. Owing to the pre-computed inverted index, it supports fast ad-hoc search but incurs the vocabulary mismatch problem. Although…

In any ranking system, the retrieval model outputs a single score for a document based on its belief on how relevant it is to a given search query. While retrieval models have continued to improve with the introduction of increasingly…

Retrieval-Augmented Generation (RAG) has emerged as a powerful paradigm for enhancing the capabilities of large language models. However, existing RAG evaluation predominantly focuses on text retrieval and relies on opaque, end-to-end…

Knowledge-intensive tasks, particularly open-domain question answering (ODQA), document reranking, and retrieval-augmented language modeling, require a balance between retrieval accuracy and generative flexibility. Traditional retrieval…

Multimodal large language models (MLLMs) achieve strong performance on benchmarks that evaluate text, image, or video understanding separately. However, these settings do not assess a critical real-world requirement, which involves…

Evaluating whether Multimodal Large Language Models can produce trustworthy, verifiable reasoning over long, visually rich documents requires evaluation beyond end-to-end answer accuracy. We introduce DocScope, a benchmark that formulates…

This study introduces De-DSI, a novel framework that fuses large language models (LLMs) with genuine decentralization for information retrieval, particularly employing the differentiable search index (DSI) concept in a decentralized…

Dense retrieval systems increasingly need to handle complex queries. In many realistic settings, users express intent through long instructions or task-specific descriptions, while target documents remain relatively simple and static. This…

Multimodal Large Language Models (MLLMs) have recently been applied to universal multimodal retrieval, where Chain-of-Thought (CoT) reasoning improves candidate reranking. However, existing approaches remain largely language-driven, relying…

Multi-modal retrieval becomes increasingly popular in practice. However, the existing retrievers are mostly text-oriented, which lack the capability to process visual information. Despite the presence of vision-language models like CLIP,…

As queries in retrieval-augmented generation (RAG) pipelines powered by large language models (LLMs) become increasingly complex and diverse, dense retrieval models have demonstrated strong performance in semantic matching. Nevertheless,…

Visual-language models (VLMs) excel at data mappings, but real-world document heterogeneity and unstructuredness disrupt the consistency of cross-modal embeddings. Recent late-interaction methods enhance image-text alignment through…

The success of DeepSeek-R1 demonstrates the immense potential of using reinforcement learning (RL) to enhance LLMs' reasoning capabilities. This paper introduces Retrv-R1, the first R1-style MLLM specifically designed for multimodal…

Scientific document retrieval is a critical task for enabling knowledge discovery and supporting research across diverse domains. However, existing dense retrieval methods often struggle to capture fine-grained scientific concepts in texts…