English
Related papers

Related papers: Benchmarking Google Embeddings 2 against Open-Sour…

200 papers

We present F2LLM-v2, a new family of general-purpose, multilingual embedding models in 8 distinct sizes ranging from 80M to 14B. Trained on a newly curated composite of 60 million publicly available high-quality data samples, F2LLM-v2…

Computation and Language · Computer Science 2026-03-20 Ziyin Zhang , Zihan Liao , Hang Yu , Peng Di , Rui Wang

Retrieval-Augmented Generation (RAG) systems have been popular for generative applications, powering language models by injecting external knowledge. Companies have been trying to leverage their large catalog of documents (e.g. PDFs,…

We present Gecko, a compact and versatile text embedding model. Gecko achieves strong retrieval performance by leveraging a key idea: distilling knowledge from large language models (LLMs) into a retriever. Our two-step distillation process…

Large language models (LLMs) are increasingly deployed in the telecommunications domain for critical tasks, relying heavily on Retrieval-Augmented Generation (RAG) to adapt general-purpose models to continuously evolving standards. However,…

Machine Learning · Computer Science 2026-04-21 Pranshav Gajjar , Vijay K Shah

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…

Computation and Language · Computer Science 2025-11-03 Qi Liu , Yanzhao Zhang , Mingxin Li , Dingkun Long , Pengjun Xie , Jiaxin Mao

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…

Computation and Language · Computer Science 2025-07-17 Chandana Cheerla

We present our system for the BLEMORE Challenge at FG 2026 on blended emotion recognition with relative salience prediction. Our approach combines six encoder families through late probability fusion: an S4D-ViTMoE face encoder adapted with…

Computer Vision and Pattern Recognition · Computer Science 2026-03-26 Masoumeh Chapariniya , Aref Farhadipour , Sarah Ebling , Volker Dellwo , Teodora Vukovic

Retrieval-Augmented Generation (RAG) has emerged as a promising paradigm for grounding large language model (LLM) outputs in retrieved evidence, thereby reducing hallucination and improving factual accuracy. Its efficacy, however, remains…

Computation and Language · Computer Science 2026-05-22 Sereiwathna Ros , Phannet Pov , Ratanaktepi Chhor , Kimleang Ly , Wan-Sup Cho , Saksonita Khoeurn

Vector search and retrieval-augmented generation (RAG) rest on the assumption that cosine similarity between text embeddings reflects conceptual relatedness. We measure where this assumption breaks. We build an augmented citation graph over…

Information Retrieval · Computer Science 2026-05-11 Junseon Yoo

Effective medical text retrieval requires both high accuracy and low latency. While LLM-based embedding models possess powerful retrieval capabilities, their prohibitive latency and high computational cost limit their application in…

Information Retrieval · Computer Science 2026-04-21 Angqing Jiang , Jianlyu Chen , Zhe Fang , Yongcan Wang , Xinpeng Li , Keyu Ding , Defu Lian

This report benchmarks the performance of ENGINEERING Ingegneria Informatica S.p.A.'s EngGPT2MoE-16B-A3B LLM, a 16B parameter Mixture of Experts (MoE) model with 3B active parameters. Performance is investigated across a wide variety of…

Computation and Language · Computer Science 2026-05-21 Andrea Sassella , Andrea Chizzola , Tommaso Bianchi , Luca Alessandrelli , Mark James Carman

Tokenization and sub-tokenization based models like word2vec, BERT and the GPTs are the state-of-the-art in natural language processing. Typically, these approaches have limitations with respect to their input representation. They fail to…

Computation and Language · Computer Science 2026-02-26 Felix Schneider , Maria Gogolev , Sven Sickert , Joachim Denzler

Vector embeddings have become ubiquitous tools for many language-related tasks. A leading embedding model is OpenAI's text-ada-002 which can embed approximately 6,000 words into a 1,536-dimensional vector. While powerful, text-ada-002 is…

Computation and Language · Computer Science 2023-06-23 Andrew Kean Gao

In retrieval applications, binary hashes are known to offer significant improvements in terms of both memory and speed. We investigate the compression of sentence embeddings using a neural encoder-decoder architecture, which is trained by…

Information Retrieval · Computer Science 2019-08-16 Felix Hamann , Nadja Kurz , Adrian Ulges

Modern retrieval-augmented generation (RAG) systems treat vector embeddings as static, context-free artifacts: an embedding has no notion of when it was created, how trustworthy its source is, or which other embeddings depend on it. This…

Information Retrieval · Computer Science 2026-04-23 Naizhong Xu

This technical report presents the training methodology and evaluation results of the open-source dewey_en_beta embedding model. The increasing demand for retrieval-augmented generation (RAG) systems and the expanding context window…

Information Retrieval · Computer Science 2025-03-27 Dun Zhang , Panxiang Zou , Yudong Zhou

We study retrieval design for code-focused generation tasks under realistic compute budgets. Using two complementary tasks from Long Code Arena -- code completion and bug localization -- we systematically compare retrieval configurations…

Machine Learning · Computer Science 2025-10-24 Timur Galimzyanov , Olga Kolomyttseva , Egor Bogomolov

ELMo embeddings (Peters et. al, 2018) had a huge impact on the NLP community and may recent publications use these embeddings to boost the performance for downstream NLP tasks. However, integration of ELMo embeddings in existent NLP…

Computation and Language · Computer Science 2019-04-08 Nils Reimers , Iryna Gurevych

Retrieval-augmented generation (RAG) over long documents typically involves splitting the text into smaller chunks, which serve as the basic units for retrieval. However, due to dependencies across the original document, contextual…

Computation and Language · Computer Science 2026-04-22 Junjie Wu , Jiangnan Li , Yuqing Li , Lemao Liu , Liyan Xu , Jiwei Li , Dit-Yan Yeung , Jie Zhou , Mo Yu

Large Language Models (LLMs) have achieved impressive progress in natural language processing, but their limited ability to retain long-term context constrains performance on document-level or multi-turn tasks. Retrieval-Augmented…

Computation and Language · Computer Science 2025-05-20 Zhangyu Wang , Siyuan Gao , Rong Zhou , Hao Wang , Li Ning