# Linq-Embed-Mistral Technical Report

arXiv: https://arxiv.org/abs/2412.03223 · HTML: https://mlsanity.com/paper/2412.03223/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 13 references that are in the map.
- First posted on arXiv 4 Dec 2024.

## Builds on (most cited first, 12 of 12)

- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [Text Embeddings by Weakly-Supervised Contrastive Pre-training](https://mlsanity.com/paper/2212.03533/) (2022)
- [Unsupervised Dense Information Retrieval with Contrastive Learning](https://mlsanity.com/paper/2112.09118/) (2021)
- [C-Pack: Packed Resources For General Chinese Embeddings](https://mlsanity.com/paper/2309.07597/) (2023)
- [Text and Code Embeddings by Contrastive Pre-Training](https://mlsanity.com/paper/2201.10005/) (2022)
- [Large Language Models for Information Retrieval: A Survey](https://mlsanity.com/paper/2308.07107/) (2023)
- [Improving Text Embeddings with Large Language Models](https://mlsanity.com/paper/2401.00368/) (2023)
- [Promptagator: Few-shot Dense Retrieval From 8 Examples](https://mlsanity.com/paper/2209.11755/) (2022)
- [Generative Representational Instruction Tuning](https://mlsanity.com/paper/2402.09906/) (2024)
- [Gecko: Versatile Text Embeddings Distilled from Large Language Models](https://mlsanity.com/paper/2403.20327/) (2024)
- [A Survey on Retrieval-Augmented Text Generation for Large Language Models](https://mlsanity.com/paper/2404.10981/) (2024)
- [InPars-v2: Large Language Models as Efficient Dataset Generators for Information Retrieval](https://mlsanity.com/paper/2301.01820/) (2023)

## Built on by (most cited first, 20 of 20)

- [EditLens: Quantifying the Extent of AI Editing in Text](https://mlsanity.com/paper/2510.03154/) (2025)
- [Guided Query Refinement: Multimodal Hybrid Retrieval with Test-Time Optimization](https://mlsanity.com/paper/2510.05038/) (2025)
- [CSRv2: Unlocking Ultra-Sparse Embeddings](https://mlsanity.com/paper/2602.05735/) (2026)
- [Overview of the TalentCLEF 2025: Skill and Job Title Intelligence for Human Capital Management](https://mlsanity.com/paper/2507.13275/) (2025)
- [Provably Safe Model Updates](https://mlsanity.com/paper/2512.01899/) (2025)
- [How Do Decoder-Only LLMs Perceive Users? Rethinking Attention Masking for User Representation Learning](https://mlsanity.com/paper/2602.10622/) (2026)
- [Overview of the Plagiarism Detection Task at PAN 2025](https://mlsanity.com/paper/2510.06805/) (2025)
- [On the Robustness of Multilingual Text Embedding Rankings Across Learning Tasks, Languages, and Benchmark Datasets](https://mlsanity.com/paper/2605.31142/) (2026)
- [LMAR: Language Model Augmented Retriever for Domain-specific Knowledge Indexing](https://mlsanity.com/paper/2508.05672/) (2025)
- [GridCodex: A RAG-Driven AI Framework for Power Grid Code Reasoning and Compliance](https://mlsanity.com/paper/2508.12682/) (2025)
- [No More K-means: Single-Stage Sparse Coding for Efficient Multi-Vector Retrieval](https://mlsanity.com/paper/2605.30120/) (2026)
- [Scaling Electronic Health Record Foundation Models for Population Health Management](https://mlsanity.com/paper/2506.00209/) (2025)
- [Data Curation Matters: Model Collapse and Spurious Shift Performance Prediction from Training on Uncurated Text Embeddings](https://mlsanity.com/paper/2506.17989/) (2025)
- [KD-Judge: A Knowledge-Driven Automated Judge Framework for Functional Fitness Movements on Edge Devices](https://mlsanity.com/paper/2604.19834/) (2026)
- [Task-Adaptive Embedding Refinement via Test-time LLM Guidance](https://mlsanity.com/paper/2605.12487/) (2026)
- [BitNet Text Embeddings](https://mlsanity.com/paper/2606.25674/) (2026)
- [MTEB-BR: A Text Embedding Benchmark for Brazilian Portuguese](https://mlsanity.com/paper/2607.04581/) (2026)
- [Exploring Block Anomaly Detection In HDFS Log Data Analysis](https://mlsanity.com/paper/2607.29383/) (2026)
- [Auditing Privacy Risks in LLM-Enhanced Graph Neural Networks](https://mlsanity.com/paper/2608.25727/) (2026)
- [Bridging the EHR Divide: Asymmetric Contrastive Learning for Cross-National Medical Representation Transfer](https://mlsanity.com/paper/2610.04946/) (2026)

## Abstract (arXiv)

This report explores the enhancement of text retrieval performance using advanced data refinement techniques. We develop Linq-Embed-Mistralfootnoteurlhttps://huggingface.co/Linq-AI-Research/Linq-Embed-Mistral by building on the E5-mistral and Mistral-7B-v0.1 models, focusing on sophisticated data crafting, data filtering, and negative mining methods, which are highly tailored to each task, applied to both existing benchmark dataset and highly tailored synthetic dataset generated via large language models (LLMs). Linq-Embed-Mistral excels in the MTEB benchmarks (as of May 29, 2024), achieving an average score of 68.2 across 56 datasets, and ranks 1st among all models for retrieval tasks on the MTEB leaderboard with a performance score of 60.2. This performance underscores its superior capability in enhancing search precision and reliability. Our contributions include advanced data refinement methods that significantly improve model performance on benchmark and synthetic datasets, techniques for homogeneous task ordering and mixed task fine-tuning to enhance model generalization and stability, and a streamlined evaluation process using 4-bit precision and a light retrieval evaluation set, which accelerates validation without sacrificing accuracy.