Pith. sign in

REVIEW 9 cited by

Linq-Embed-Mistral Technical Report

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2412.03223 v1 pith:7MQHA7X3 submitted 2024-12-04 cs.CL

Chanyeol Choi , Junseong Kim , Seolhwa Lee , Jihoon Kwon , Sangmo Gu , Yejin Kim , Minkyung Cho , Jy-yong Sohn This is my paper · ORCID
classification cs.CL
keywords datalinq-embed-mistralperformancemodelsretrievaltaskadvancedbenchmark
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

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 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.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 9 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. BitNet Text Embeddings

    cs.CL 2026-06 unverdicted novelty 6.0 of 10

    BITEMBED trains 1.58-bit ternary-weight LLM embedders with contrastive pre-training, supervised distillation, and multi-precision output training, matching FP16 teachers within ~0.6 MMTEB points at ~2x CPU speed.

  2. KD-Judge: A Knowledge-Driven Automated Judge Framework for Functional Fitness Movements on Edge Devices

    cs.CV 2026-04 unverdicted novelty 6.0 of 10

    KD-Judge structures fitness rules via LLM retrieval and chain-of-thought, then uses pose-guided kinematics for rule-based rep validation with caching for efficient edge deployment, achieving RTF < 1 and speedups up to...

  3. FinTexTS: Financial Text-Paired Time-Series Dataset via Semantic-Based and Multi-Level Pairing

    cs.AI 2026-03 conditional novelty 6.0 of 10

    A new dataset and pairing framework links stock prices to semantically relevant news at macro, sector, related-company, and target-company levels, improving stock forecast accuracy over keyword-based pairing.

  4. THEME: Enhancing Thematic Investing with Semantic Stock Representations and Temporal Dynamics

    q-fin.PM 2025-08 conditional novelty 6.0 of 10

    A hierarchical contrastive learning framework that aligns stocks with theme descriptions and refines embeddings with short-term return signals improves thematic retrieval and backtested portfolio metrics.

  5. Beyond Representational Similarity: Source-Conditioned Description-Length Gain for Generative Plagiarism Detection and Candidate Source Reranking

    cs.CL 2026-08 conditional novelty 5.0 of 10

    A frozen language model's log-likelihood gain from source conditioning, aggregated as SCDG, outperforms lexical, embedding, and prompted-LLM baselines for generative plagiarism detection and source reranking.

  6. Overview of the TalentCLEF 2025: Skill and Job Title Intelligence for Human Capital Management

    cs.CL 2025-07 conditional novelty 5.0 of 10

    TalentCLEF 2025 publishes the first public multilingual benchmark for job title matching and skill prediction, with results showing training strategy matters more than model size.

  7. Conventional Contrastive Learning Often Falls Short: Improving Dense Retrieval with Cross-Encoder Listwise Distillation and Synthetic Data

    cs.IR 2025-05 conditional novelty 5.0 of 10

    Contrastive fine-tuning often degrades strong dense retrievers, while combining cross-encoder listwise distillation with diverse synthetic queries consistently improves them.

  8. Exploring Block Anomaly Detection In HDFS Log Data Analysis

    cs.LG 2026-07 conditional novelty 4.0 of 10

    An LLM-BiLSTM hybrid model detects anomalous HDFS log blocks with 94.8% F1 on the Loghub HDFS dataset, outperforming DeepLog.

  9. Data Curation Matters: Model Collapse and Spurious Shift Performance Prediction from Training on Uncurated Text Embeddings

    cs.LG 2025-06 conditional novelty 4.0 of 10

    Training on LLM text embeddings can cause tabular classifiers to collapse to single-class predictions, which spuriously inflates Accuracy-on-the-Line correlations.

Pith tools