中文
相关论文

相关论文: Granite Embedding Multilingual R2 Models

200 篇论文

General-purpose multilingual vector representations, used in retrieval, regression and classification, are traditionally obtained from bidirectional encoder models. Despite their wide applicability, encoders have been recently overshadowed…

Large Language Models (LLMs) have consistently showcased remarkable generalization capabilities when applied to various language tasks. Nonetheless, harnessing the full potential of LLMs for Radiology Report Generation (R2Gen) still…

计算机视觉与模式识别 · 计算机科学 2023-11-07 Zhanyu Wang , Lingqiao Liu , Lei Wang , Luping Zhou

Contextualized embeddings based on large language models (LLMs) are available for various languages, but their coverage is often limited for lower resourced languages. Using LLMs for such languages is often difficult due to a high…

计算与语言 · 计算机科学 2025-01-28 Daniil Gurgurov , Rishu Kumar , Simon Ostermann

Words have been represented in a high-dimensional vector space that encodes their semantic similarities, enabling downstream applications such as retrieving synonyms, antonyms, and relevant contexts. However, despite recent advances in…

计算与语言 · 计算机科学 2024-09-25 Genta Indra Winata , Ruochen Zhang , David Ifeoluwa Adelani

We introduce FIN-bench-v2, a unified benchmark suite for evaluating large language models in Finnish. FIN-bench-v2 consolidates Finnish versions of widely used benchmarks together with an updated and expanded version of the original…

计算与语言 · 计算机科学 2025-12-16 Joona Kytöniemi , Jousia Piha , Akseli Reunamo , Fedor Vitiugin , Farrokh Mehryary , Sampo Pyysalo

Encoder-only languages models are frequently used for a variety of standard machine learning tasks, including classification and retrieval. However, there has been a lack of recent research for encoder models, especially with respect to…

计算与语言 · 计算机科学 2025-09-09 Marc Marone , Orion Weller , William Fleshman , Eugene Yang , Dawn Lawrie , Benjamin Van Durme

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…

计算与语言 · 计算机科学 2025-09-03 Yuxiang Liu , Tian Wang , Gourab Kundu , Tianyu Cao , Guang Cheng , Zhen Ge , Jianshu Chen , Qingjun Cui , Trishul Chilimbi

In this work, we present a comprehensive exploration of finetuning Malaysian language models, specifically Llama2 and Mistral, on embedding tasks involving negative and positive pairs. We release two distinct models tailored for Semantic…

计算与语言 · 计算机科学 2024-02-06 Husein Zolkepli , Aisyah Razak , Kamarul Adha , Ariff Nazhan

The rapid advancement of code large language models (LLMs) has sparked significant research interest in systematically evaluating their code generation capabilities, yet existing benchmarks predominantly assess models at a single structural…

计算与语言 · 计算机科学 2025-12-30 Fanglin Xu , Wei Zhang , Jian Yang , Guo Chen , Aishan Liu , Zhoujun Li , Xianglong Liu , Bryan Dai

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…

计算机视觉与模式识别 · 计算机科学 2025-11-03 Weijian Jian , Yajun Zhang , Dawei Liang , Chunyu Xie , Yixiao He , Dawei Leng , Yuhui Yin

Organizations increasingly rely on proprietary enterprise data, including HR records, structured reports, and tabular documents, for critical decision-making. While Large Language Models (LLMs) have strong generative capabilities, they are…

计算与语言 · 计算机科学 2025-07-17 Chandana Cheerla

Multi-vector dense models, such as ColBERT, have proven highly effective in information retrieval. ColBERT's late interaction scoring approximates the joint query-document attention seen in cross-encoders while maintaining inference…

Most organizational data in this world are stored as documents, and visual retrieval plays a crucial role in unlocking the collective intelligence from all these documents. However, existing benchmarks focus on English-only document…

计算机视觉与模式识别 · 计算机科学 2025-08-26 Jian Chen , Ming Li , Jihyung Kil , Chenguang Wang , Tong Yu , Ryan Rossi , Tianyi Zhou , Changyou Chen , Ruiyi Zhang

Text embeddings are central to modern information retrieval and Retrieval-Augmented Generation (RAG). While dense models derived from Large Language Models (LLMs) dominate current practice, recent work has explored quantum-inspired…

信息检索 · 计算机科学 2026-04-14 Dario Maio

While Ferret seamlessly integrates regional understanding into the Large Language Model (LLM) to facilitate its referring and grounding capability, it poses certain limitations: constrained by the pre-trained fixed visual encoder and failed…

计算机视觉与模式识别 · 计算机科学 2024-04-12 Haotian Zhang , Haoxuan You , Philipp Dufter , Bowen Zhang , Chen Chen , Hong-You Chen , Tsu-Jui Fu , William Yang Wang , Shih-Fu Chang , Zhe Gan , Yinfei Yang

Dense vector representations for textual data are crucial in modern NLP. Word embeddings and sentence embeddings estimated from raw texts are key in achieving state-of-the-art results in various tasks requiring semantic understanding.…

计算与语言 · 计算机科学 2023-07-06 Sonal Sannigrahi , Josef van Genabith , Cristina Espana-Bonet

The remarkable success of multimodal large language models (MLLMs) has driven advances in multimodal embeddings, yet existing models remain inherently discriminative, limiting their ability to benefit from reasoning-driven generation…

机器学习 · 计算机科学 2026-03-03 Zhibin Lan , Liqiang Niu , Fandong Meng , Jie Zhou , Jinsong Su

Massively multilingual sentence representation models, e.g., LASER, SBERT-distill, and LaBSE, help significantly improve cross-lingual downstream tasks. However, the use of a large amount of data or inefficient model architectures results…

计算与语言 · 计算机科学 2024-05-31 Zhuoyuan Mao , Chenhui Chu , Sadao Kurohashi

Training effective multilingual embedding models presents unique challenges due to the diversity of languages and task objectives. Although small multilingual models (<1 B parameters) perform well on multilingual tasks generally, they…

计算与语言 · 计算机科学 2026-04-23 Lifu Tu , Yingbo Zhou , Semih Yavuz