Related papers: ReasonEmbed: Enhanced Text Embeddings for Reasonin…

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…

Effectively adapting powerful pretrained foundation models to diverse tasks remains a key challenge in AI deployment. Current approaches primarily follow two paradigms:discrete optimization of text prompts through prompt engineering, or…

Retrieval-augmented generation (RAG) systems trained using reinforcement learning (RL) with reasoning are hampered by inefficient context management, where long, noisy retrieved documents increase costs and degrade performance. We introduce…

As multimodal content continues to expand at a rapid pace, audio retrieval has emerged as a key enabling technology for media search, content organization, and intelligent assistants. However, most existing benchmarks concentrate on…

Text embedding representing natural language documents in a semantic vector space can be used for document retrieval using nearest neighbor lookup. In order to study the feasibility of neural models specialized for retrieval in a…

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…

This report explores the enhancement of text retrieval performance using advanced data refinement techniques. We develop Linq-Embed-Mistral\footnote{\url{https://huggingface.co/Linq-AI-Research/Linq-Embed-Mistral}} by building on the…

We present a novel approach for training small language models for reasoning-intensive document ranking that combines knowledge distillation with reinforcement learning optimization. While existing methods often rely on expensive human…

Retrieval-Augmented Generation (RAG) systems in chemistry heavily depend on accurate and relevant retrieval of chemical literature. However, general-purpose text embedding models frequently fail to adequately represent complex chemical…

In this paper, we introduce a new embedding model called M3-Embedding, which is distinguished for its versatility in \textit{Multi-Linguality}, \textit{Multi-Functionality}, and \textit{Multi-Granularity}. It provides a uniform support for…

Recent text-guided image editing (TIE) models have achieved remarkable progress, however, many edited results still suffer from artifacts, unintended modifications, and suboptimal aesthetics. Although several benchmarks and evaluation…

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…

Recent dense retrievers increasingly leverage the robust text understanding capabilities of Large Language Models (LLMs), encoding queries and documents into a shared embedding space for effective retrieval. However, most existing methods…

Reasoning-based large language models have excelled in mathematics and programming, yet their potential in knowledge-intensive medical question answering remains underexplored and insufficiently validated in clinical contexts. To bridge…

Despite the success of text retrieval in many NLP tasks, code retrieval remains a largely underexplored area. Most text retrieval systems are tailored for natural language queries, often neglecting the specific challenges of retrieving…

Unlike traditional fact-based retrieval, rationale-based retrieval typically necessitates cross-encoding of query-document pairs using large language models, incurring substantial computational costs. To address this limitation, we propose…

We present ReMatch, a framework that leverages the generative strength of MLLMs for multimodal retrieval. Previous approaches treated an MLLM as a simple encoder, ignoring its generative nature, and under-utilising its compositional…

Transformer-based models such as BERT and E5 have significantly advanced text embedding by capturing rich contextual representations. However, many complex real-world queries require sophisticated reasoning to retrieve relevant documents…

Despite their remarkable natural language understanding capabilities, Large Language Models (LLMs) have been underutilized for retrieval tasks. We present Search-R3, a novel framework that addresses this limitation by adapting LLMs to…

This paper introduces RETSim (Resilient and Efficient Text Similarity), a lightweight, multilingual deep learning model trained to produce robust metric embeddings for near-duplicate text retrieval, clustering, and dataset deduplication…