{"total":108,"rows":[{"id":"2210.07316","title":"MTEB: Massive Text Embedding Benchmark","created":"2022-10-13","cited_by_count":640,"area":null},{"id":"2202.08904","title":"SGPT: GPT Sentence Embeddings for Semantic Search","created":"2022-02-17","cited_by_count":204,"area":null},{"id":"2108.05542","title":"AMMUS : A Survey of Transformer-based Pretrained Models in Natural Language Processing","created":"2021-08-12","cited_by_count":131,"area":null},{"id":"2112.07577","title":"GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation of Dense Retrieval","created":"2021-12-14","cited_by_count":119,"area":null},{"id":"2205.12035","title":"RetroMAE: Pre-Training Retrieval-oriented Language Models Via Masked Auto-Encoder","created":"2022-05-24","cited_by_count":118,"area":null},{"id":"2106.07345","title":"Self-Guided Contrastive Learning for BERT Sentence Representations","created":"2021-06-03","cited_by_count":103,"area":null},{"id":"2205.04733","title":"From Distillation to Hard Negative Sampling: Making Sparse Neural IR Models More Effective","created":"2022-05-10","cited_by_count":98,"area":null},{"id":"2212.02027","title":"Retrieval as Attention: End-to-end Learning of Retrieval and Reading within a Single Transformer","created":"2022-12-05","cited_by_count":45,"area":null},{"id":"2201.12093","title":"PCL: Peer-Contrastive Learning with Diverse Augmentations for Unsupervised Sentence Embeddings","created":"2022-01-28","cited_by_count":29,"area":null},{"id":"2305.16726","title":"RankCSE: Unsupervised Sentence Representations Learning via Learning to Rank","created":"2023-05-26","cited_by_count":23,"area":null},{"id":"2110.08552","title":"Virtual Augmentation Supported Contrastive Learning of Sentence Representations","created":"2021-10-16","cited_by_count":21,"area":null},{"id":"2203.02679","title":"Just Rank: Rethinking Evaluation with Word and Sentence Similarities","created":"2022-03-05","cited_by_count":20,"area":null},{"id":"2210.15212","title":"COCO-DR: Combating Distribution Shifts in Zero-Shot Dense Retrieval with Contrastive and Distributionally Robust Learning","created":"2022-10-27","cited_by_count":20,"area":null},{"id":"2408.12503","title":"The Russian-focused embedders' exploration: ruMTEB benchmark and Russian embedding model design","created":"2024-08-22","cited_by_count":20,"area":null},{"id":"2210.16798","title":"Generate, Discriminate and Contrast: A Semi-Supervised Sentence Representation Learning Framework","created":"2022-10-30","cited_by_count":19,"area":null},{"id":"2310.01732","title":"Nugget: Neural Agglomerative Embeddings of Text","created":"2023-10-03","cited_by_count":19,"area":null},{"id":"2405.10138","title":"PL-MTEB: Polish Massive Text Embedding Benchmark","created":"2024-05-16","cited_by_count":19,"area":null},{"id":"2301.00709","title":"Tsetlin Machine Embedding: Representing Words Using Logical Expressions","created":"2023-01-02","cited_by_count":15,"area":null},{"id":"2508.06199","title":"Benchmarking Pretrained Molecular Embedding Models For Molecular Representation Learning","created":"2025-08-08","cited_by_count":15,"area":null},{"id":"2208.03197","title":"Low-Resource Dense Retrieval for Open-Domain Question Answering: A Comprehensive Survey","created":"2022-08-05","cited_by_count":14,"area":null},{"id":"2402.05617","title":"Deep Learning-based Computational Job Market Analysis: A Survey on Skill Extraction and Classification from Job Postings","created":"2024-02-08","cited_by_count":14,"area":null},{"id":"2305.02564","title":"RetroMAE-2: Duplex Masked Auto-Encoder For Pre-Training Retrieval-Oriented Language Models","created":"2023-05-04","cited_by_count":13,"area":null},{"id":"2401.02709","title":"German Text Embedding Clustering Benchmark","created":"2024-01-05","cited_by_count":13,"area":null},{"id":"2210.08474","title":"Sentence Representation Learning with Generative Objective rather than Contrastive Objective","created":"2022-10-16","cited_by_count":12,"area":null},{"id":"2305.12641","title":"A Comprehensive Survey of Sentence Representations: From the BERT Epoch to the ChatGPT Era and Beyond","created":"2023-05-22","cited_by_count":12,"area":null},{"id":"2207.12759","title":"Training Effective Neural Sentence Encoders from Automatically Mined Paraphrases","created":"2022-07-26","cited_by_count":11,"area":null},{"id":"2209.09433","title":"Non-Linguistic Supervision for Contrastive Learning of Sentence Embeddings","created":"2022-09-20","cited_by_count":10,"area":null},{"id":"2506.08354","title":"Position: Text Embeddings Should Capture Implicit Semantics, Not Just Surface Meaning","created":"2025-06-10","cited_by_count":10,"area":null},{"id":"2407.10691","title":"$\\texttt{MixGR}$: Enhancing Retriever Generalization for Scientific Domain through Complementary Granularity","created":"2024-07-15","cited_by_count":9,"area":null},{"id":"2312.14106","title":"Learning Human-like Representations to Enable Learning Human Values","created":"2023-12-21","cited_by_count":7,"area":null},{"id":"2403.18933","title":"SemEval-2024 Task 1: Semantic Textual Relatedness for African and Asian Languages","created":"2024-03-27","cited_by_count":7,"area":null},{"id":"2211.03348","title":"Contrastive Learning with Prompt-derived Virtual Semantic Prototypes for Unsupervised Sentence Embedding","created":"2022-11-07","cited_by_count":6,"area":null},{"id":"2305.01713","title":"Learning Disentangled Semantic Spaces of Explanations via Invertible Neural Networks","created":"2023-05-02","cited_by_count":6,"area":null},{"id":"2310.16193","title":"Length is a Curse and a Blessing for Document-level Semantics","created":"2023-10-24","cited_by_count":6,"area":null},{"id":"2405.20468","title":"MTEB-French: Resources for French Sentence Embedding Evaluation and Analysis","created":"2024-05-30","cited_by_count":6,"area":null},{"id":"2602.05735","title":"CSRv2: Unlocking Ultra-Sparse Embeddings","created":"2026-02-05","cited_by_count":6,"area":null},{"id":"2210.13749","title":"AugCSE: Contrastive Sentence Embedding with Diverse Augmentations","created":"2022-10-20","cited_by_count":5,"area":null},{"id":"2210.17167","title":"Reduce Catastrophic Forgetting of Dense Retrieval Training with Teleportation Negatives","created":"2022-10-31","cited_by_count":5,"area":null},{"id":"2305.14599","title":"Bridging Continuous and Discrete Spaces: Interpretable Sentence Representation Learning via Compositional Operations","created":"2023-05-24","cited_by_count":5,"area":null},{"id":"2306.16143","title":"Generative User-Experience Research for Developing Domain-specific Natural Language Processing Applications","created":"2023-06-28","cited_by_count":5,"area":null},{"id":"2312.15784","title":"AHAM: Adapt, Help, Ask, Model -- Harvesting LLMs for literature mining","created":"2023-12-25","cited_by_count":5,"area":null},{"id":"2503.02056","title":"CareerBERT: Matching Resumes to ESCO Jobs in a Shared Embedding Space for Generic Job Recommendations","created":"2025-03-03","cited_by_count":5,"area":null},{"id":"2507.21500","title":"VN-MTEB: Vietnamese Massive Text Embedding Benchmark","created":"2025-07-29","cited_by_count":5,"area":null},{"id":"2201.00365","title":"Establishing Strong Baselines for TripClick Health Retrieval","created":"2022-01-02","cited_by_count":4,"area":null},{"id":"2206.10029","title":"SynWMD: Syntax-aware Word Mover's Distance for Sentence Similarity Evaluation","created":"2022-06-20","cited_by_count":4,"area":null},{"id":"2212.08802","title":"Relational Sentence Embedding for Flexible Semantic Matching","created":"2022-12-17","cited_by_count":4,"area":null},{"id":"2303.12848","title":"Test-time Detection and Repair of Adversarial Samples via Masked Autoencoder","created":"2023-03-22","cited_by_count":4,"area":null},{"id":"2311.15564","title":"Boot and Switch: Alternating Distillation for Zero-Shot Dense Retrieval","created":"2023-11-27","cited_by_count":4,"area":null},{"id":"2312.02803","title":"Leveraging Domain Adaptation and Data Augmentation to Improve Qur'anic IR in English and Arabic","created":"2023-12-05","cited_by_count":4,"area":null},{"id":"2401.13621","title":"DenoSent: A Denoising Objective for Self-Supervised Sentence Representation Learning","created":"2024-01-24","cited_by_count":4,"area":null},{"id":"2406.12634","title":"News Without Borders: Domain Adaptation of Multilingual Sentence Embeddings for Cross-lingual News Recommendation","created":"2024-06-18","cited_by_count":4,"area":null},{"id":"2407.19527","title":"Open Sentence Embeddings for Portuguese with the Serafim PT* encoders family","created":"2024-07-28","cited_by_count":4,"area":null},{"id":"2409.12887","title":"Enhancing Unsupervised Sentence Embeddings via Knowledge-Driven Data Augmentation and Gaussian-Decayed Contrastive Learning","created":"2024-09-19","cited_by_count":4,"area":null},{"id":"2501.10175","title":"Multi-stage Training of Bilingual Islamic LLM for Neural Passage Retrieval","created":"2025-01-17","cited_by_count":4,"area":null},{"id":"2110.02030","title":"Exploiting Twitter as Source of Large Corpora of Weakly Similar Pairs for Semantic Sentence Embeddings","created":"2021-10-05","cited_by_count":3,"area":null},{"id":"2110.12000","title":"Bank transactions embeddings help to uncover current macroeconomics","created":"2021-10-14","cited_by_count":3,"area":null},{"id":"2202.02990","title":"Comparison and Combination of Sentence Embeddings Derived from Different Supervision Signals","created":"2022-02-07","cited_by_count":3,"area":null},{"id":"2203.06591","title":"ORDSIM: Ordinal Regression for E-Commerce Query Similarity Prediction","created":"2022-03-13","cited_by_count":3,"area":null},{"id":"2204.03251","title":"Towards Automatic Construction of Filipino WordNet: Word Sense Induction and Synset Induction Using Sentence Embeddings","created":"2022-04-07","cited_by_count":3,"area":null},{"id":"2311.00408","title":"AdaSent: Efficient Domain-Adapted Sentence Embeddings for Few-Shot Classification","created":"2023-11-01","cited_by_count":3,"area":null},{"id":"2311.13921","title":"Some Like It Small: Czech Semantic Embedding Models for Industry Applications","created":"2023-11-23","cited_by_count":3,"area":null},{"id":"2503.00867","title":"DUAL: Diversity and Uncertainty Active Learning for Text Summarization","created":"2025-03-02","cited_by_count":3,"area":null},{"id":"2506.16552","title":"Revela: Dense Retriever Learning via Language Modeling","created":"2025-06-19","cited_by_count":3,"area":null},{"id":"2507.20783","title":"On The Role of Pretrained Language Models in General-Purpose Text Embeddings: A Survey","created":"2025-07-28","cited_by_count":3,"area":null},{"id":"2510.06730","title":"PTEB: Towards Robust Text Embedding Evaluation via Stochastic Paraphrasing at Evaluation Time with LLMs","created":"2025-10-08","cited_by_count":3,"area":null},{"id":"2210.12857","title":"Bootstrapping meaning through listening: Unsupervised learning of spoken sentence embeddings","created":"2022-10-23","cited_by_count":2,"area":null},{"id":"2211.08769","title":"RetroMAE v2: Duplex Masked Auto-Encoder For Pre-Training Retrieval-Oriented Language Models","created":"2022-11-16","cited_by_count":2,"area":null},{"id":"2310.17690","title":"Non-contrastive sentence representations via self-supervision","created":"2023-10-26","cited_by_count":2,"area":null},{"id":"2311.08533","title":"Natural Language Processing for Financial Regulation","created":"2023-11-14","cited_by_count":2,"area":null},{"id":"2312.09670","title":"Probing Pretrained Language Models with Hierarchy Properties","created":"2023-12-15","cited_by_count":2,"area":null},{"id":"2405.14437","title":"Combining Denoising Autoencoders with Contrastive Learning to fine-tune Transformer Models","created":"2024-05-23","cited_by_count":2,"area":null},{"id":"2405.19967","title":"Improved Out-of-Scope Intent Classification with Dual Encoding and Threshold-based Re-Classification","created":"2024-05-30","cited_by_count":2,"area":null},{"id":"2410.23510","title":"Tiny Transformers Excel at Sentence Compression","created":"2024-10-30","cited_by_count":2,"area":null},{"id":"2508.12243","title":"SEA-BED: How Do Embedding Models Represent Southeast Asian Languages?","created":"2025-08-17","cited_by_count":2,"area":null},{"id":"2601.04768","title":"LANGSAE EDITING: Improving Multilingual Information Retrieval via Post-hoc Language Identity Removal","created":"2026-01-08","cited_by_count":2,"area":null},{"id":"2202.13802","title":"A Mutually Reinforced Framework for Pretrained Sentence Embeddings","created":"2022-02-28","cited_by_count":1,"area":null},{"id":"2206.08263","title":"'John ate 5 apples' != 'John ate some apples': Self-Supervised Paraphrase Quality Detection for Algebraic Word Problems","created":"2022-06-16","cited_by_count":1,"area":null},{"id":"2211.07716","title":"Zero-Shot Text Matching for Automated Auditing using Sentence Transformers","created":"2022-10-28","cited_by_count":1,"area":null},{"id":"2301.08193","title":"JCSE: Contrastive Learning of Japanese Sentence Embeddings and Its Applications","created":"2023-01-19","cited_by_count":1,"area":null},{"id":"2305.09556","title":"Adapting Sentence Transformers for the Aviation Domain","created":"2023-05-16","cited_by_count":1,"area":null},{"id":"2311.03228","title":"An Efficient Self-Supervised Cross-View Training For Sentence Embedding","created":"2023-11-06","cited_by_count":1,"area":null},{"id":"2403.15210","title":"Early Period of Training Impacts Adaptation for Out-of-Distribution Generalization: An Empirical Study","created":"2024-03-22","cited_by_count":1,"area":null},{"id":"2406.03125","title":"Space Decomposition for Sentence Embedding","created":"2024-06-05","cited_by_count":1,"area":null},{"id":"2502.15996","title":"Med-gte-hybrid: A contextual embedding transformer model for extracting actionable information from clinical texts","created":"2025-02-21","cited_by_count":1,"area":null},{"id":"2503.09094","title":"Domain Adaptation for Japanese Sentence Embeddings with Contrastive Learning based on Synthetic Sentence Generation","created":"2025-03-12","cited_by_count":1,"area":null},{"id":"2503.11426","title":"Text Compression for Efficient Language Generation","created":"2025-03-14","cited_by_count":1,"area":null},{"id":"2507.09601","title":"NMIXX: Domain-Adapted Neural Embeddings for Cross-Lingual eXploration of Finance","created":"2025-07-13","cited_by_count":1,"area":null},{"id":"2508.02945","title":"LLM-based IR-system for Bank Supervisors","created":"2025-08-04","cited_by_count":1,"area":null},{"id":"2603.21437","title":"Pooling and Semantic Shift: The Fundamental Challenges in Long Text Embedding and Retrieval","created":"2026-03-22","cited_by_count":1,"area":null},{"id":"2605.28190","title":"The Harder Text Embedding Benchmark (HTEB): Beyond One-dimensional Static Robustness","created":"2026-05-27","cited_by_count":1,"area":null},{"id":"2607.11722","title":"STEP: Career-Path Recommendation via Temporal and Educational Trajectory Modeling","created":"2026-07-13","cited_by_count":1,"area":null},{"id":"2305.15867","title":"Extracting Text Representations for Terms and Phrases in Technical Domains","created":"2023-05-25","cited_by_count":0,"area":null},{"id":"2310.13267","title":"On the Language Encoder of Contrastive Cross-modal Models","created":"2023-10-20","cited_by_count":0,"area":null},{"id":"2401.03181","title":"A Joint-Reasoning based Disease Q&A System","created":"2024-01-06","cited_by_count":0,"area":null},{"id":"2402.02932","title":"Domain Adaptation of Multilingual Semantic Search -- Literature Review","created":"2024-02-05","cited_by_count":0,"area":null},{"id":"2404.00056","title":"Fingerprinting web servers through Transformer-encoded HTTP response headers","created":"2024-03-26","cited_by_count":0,"area":null},{"id":"2410.22197","title":"Class-Aware Contrastive Optimization for Imbalanced Text Classification","created":"2024-10-29","cited_by_count":0,"area":null},{"id":"2506.23662","title":"Zero-Shot Contextual Embeddings via Offline Synthetic Corpus Generation","created":"2025-06-30","cited_by_count":0,"area":null},{"id":"2507.03415","title":"SMCLM: Semantically Meaningful Causal Language Modeling for Autoregressive Paraphrase Generation","created":"2025-07-04","cited_by_count":0,"area":null},{"id":"2508.08272","title":"Real-time News Story Identification","created":"2025-07-30","cited_by_count":0,"area":null}],"next_cursor":"100"}