mlsanityData to 14 Oct 2026

Gemini Embedding: Generalizable Embeddings from Gemini

arXiv 2503.07891 ↗First posted 10 Mar 2025cs.CL cs.AIcited by 94

Not on the map. Why?

Abstract (arXiv)

In this report, we introduce Gemini Embedding, a state-of-the-art embedding model leveraging the power of Gemini, Google's most capable large language model. Capitalizing on Gemini's inherent multilingual and code understanding capabilities, Gemini Embedding produces highly generalizable embeddings for text spanning numerous languages and textual modalities. The representations generated by Gemini Embedding can be precomputed and applied to a variety of downstream tasks including classification, similarity, clustering, ranking, and retrieval. Evaluated on the Massive Multilingual Text Embedding Benchmark (MMTEB), which includes over one hundred tasks across 250+ languages, Gemini Embedding substantially outperforms prior state-of-the-art models, demonstrating considerable improvements in embedding quality. Achieving state-of-the-art performance across MMTEB's multilingual, English, and code benchmarks, our unified model demonstrates strong capabilities across a broad selection of tasks and surpasses specialized domain-specific models.

Key facts. Cited by 94 papers in the map (data through 14 Oct 2026). Builds on 34 of its 41 references that are in the map. First posted on arXiv 10 Mar 2025.

Builds on

34 of 41 references.

References · 34

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  4. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  5. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  6. 2024Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextcited by 3,224
  7. 2021SimCSE: Simple Contrastive Learning of Sentence Embeddingscited by 2,173
  8. 2022Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference timecited by 1,396
  9. 2022Text Embeddings by Weakly-Supervised Contrastive Pre-trainingcited by 1,253
  10. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,216
  11. 2018Averaging Weights Leads to Wider Optima and Better Generalizationcited by 1,209
  12. 2023PaLM 2 Technical Reportcited by 1,162
22 more
  1. 2014Distributed Representations of Sentences and Documentscited by 678
  2. 2022MTEB: Massive Text Embedding Benchmarkcited by 640
  3. 2020Language-agnostic BERT Sentence Embeddingcited by 627
  4. 2024NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Modelscited by 472
  5. 2021Sentence-T5: Scalable Sentence Encoders from Pre-trained Text-to-Text Modelscited by 463
  6. 2021Large Dual Encoders Are Generalizable Retrieverscited by 456
  7. 2022Text and Code Embeddings by Contrastive Pre-Trainingcited by 361
  8. 2023Improving Text Embeddings with Large Language Modelscited by 303
  9. 2022Matryoshka Representation Learningcited by 282
  10. 2022Promptagator: Few-shot Dense Retrieval From 8 Examplescited by 235
  11. 2019Document Expansion by Query Predictioncited by 231
  12. 2024VLM2Vec: Training Vision-Language Models for Massive Multimodal Embedding Taskscited by 228
  13. 2025MMTEB: Massive Multilingual Text Embedding Benchmarkcited by 125
  14. 2020XOR QA: Cross-lingual Open-Retrieval Question Answeringcited by 121
  15. 2024Gecko: Versatile Text Embeddings Distilled from Large Language Modelscited by 83
  16. 2024Making Text Embedders Few-Shot Learnerscited by 79
  17. 2023InPars-v2: Large Language Models as Efficient Dataset Generators for Information Retrievalcited by 73
  18. 2023XTREME-UP: A User-Centric Scarce-Data Benchmark for Under-Represented Languagescited by 34
  19. 2018Stochastic Negative Mining for Learning with Large Output Spacescited by 29
  20. 2023Leveraging LLMs for Synthesizing Training Data Across Many Languages in Multilingual Dense Retrievalcited by 24
  21. 2025Adapting Decoder-Based Language Models for Diverse Encoder Downstream Taskscited by 10
  22. 2023SamToNe: Improving Contrastive Loss for Dual Encoder Retrieval Models with Same Tower Negativescited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 37; 2026: 57.

94 papers.

Sort:

By area:

  1. 2025Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Modelscited by 1,261
  2. 2025ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memorycited by 284
  3. 2026Qwen3-VL-Embedding and Qwen3-VL-Reranker: A Unified Framework for State-of-the-Art Multimodal Retrieval and Rankingcited by 230
  4. 2025EmbeddingGemma: Powerful and Lightweight Text Representationscited by 139
  5. 2025On the Theoretical Limitations of Embedding-Based Retrievalcited by 104
  6. 2025Llama-Embed-Nemotron-8B: A Universal Text Embedding Model for Multilingual and Cross-Lingual Taskscited by 51
  7. 2025KaLM-Embedding-V2: Superior Training Techniques and Data Inspire A Versatile Embedding Modelcited by 36
  8. 2025The Geometry of Reasoning: Flowing Logics in Representation Spacecited by 21
  9. 2025SweRank: Software Issue Localization with Code Rankingcited by 20
  10. 2025Should We Still Pretrain Encoders with Masked Language Modeling?cited by 16
  11. 2025Efficient Code Embeddings from Code Generation Modelscited by 13
  12. 2026Coding Agents are Effective Long-Context Processorscited by 12
38 more
  1. 2025SAIL-Embedding Technical Report: Omni-modal Embedding Foundation Modelcited by 10
  2. 2026Nemotron ColEmbed V2: Top-Performing Late Interaction Embedding Models for Visual Document Retrievalcited by 10
  3. 2026Gemini Embedding 2: A Native Multimodal Embedding Model from Geminicited by 10
  4. 2025Large Reasoning Embedding Models: Towards Next-Generation Dense Retrieval Paradigmcited by 9
  5. 2026Massive Sound Embedding Benchmark (MSEB)cited by 9
  6. 2026Diffusion-Pretrained Dense and Contextual Embeddingscited by 9
  7. 2025Extracting alignment data in open modelscited by 8
  8. 2026OBLIQ-Bench: Exposing Overlooked Bottlenecks in Modern Retrievers with Latent and Implicit Queriescited by 8
  9. 2025Advancing Semantic Caching for LLMs with Domain-Specific Embeddings and Synthetic Datacited by 7
  10. 2025WAVE: Learning Unified & Versatile Audio-Visual Embeddings with Multimodal LLMcited by 7
  11. 2025DS-STAR: Data Science Agent for Solving Diverse Tasks across Heterogeneous Formats and Open-Ended Queriescited by 6
  12. 2026Persona Generators: Generating Diverse Synthetic Personas for Arbitrary Contextscited by 6
  13. 2026CSRv2: Unlocking Ultra-Sparse Embeddingscited by 6
  14. 2026Real Faults in Model Context Protocol (MCP) Software: a Comprehensive Taxonomycited by 6
  15. 2026Learning Retrieval Models with Sparse Autoencoderscited by 6
  16. 2025The Other Mind: How Language Models Exhibit Human Temporal Cognitioncited by 5
  17. 2025From Topology to Retrieval: Decoding Embedding Spaces with Unified Signaturescited by 5
  18. 2026The Embedder's Dilemma: LLMs Are Better, but at What Cost?cited by 5
  19. 2025Can Large Language Models Really Recognize Your Name?cited by 4
  20. 2025LLM-guided Hierarchical Search for End-to-end Reasoning Intensive Retrievalcited by 4
  21. 2025Retrieval-GRPO: A Multi-Objective Reinforcement Learning Framework for Dense Retrieval in Taobao Searchcited by 4
  22. 2026Understanding Performance Gap Between Parallel and Sequential Sampling in Large Reasoning Modelscited by 4
  23. 2025On The Role of Pretrained Language Models in General-Purpose Text Embeddings: A Surveycited by 3
  24. 2025AfriMTEB and AfriE5: Benchmarking and Adapting Text Embedding Models for African Languagescited by 3
  25. 2026100x Cost & Latency Reduction: Performance Analysis of AI Query Approximation using Lightweight Proxy Modelscited by 3
  26. 2026LiSA: Lifelong Safety Adaptation via Conservative Policy Inductioncited by 3
  27. 2026MolEmb: Multimodal Large Language Models Can Be Strong Molecular Embedding Modelscited by 3
  28. 2025Demand Estimation with Text and Image Datacited by 2
  29. 2025BiXSE: Improving Dense Retrieval via Probabilistic Graded Relevance Distillationcited by 2
  30. 2025CoDiEmb: A Collaborative yet Distinct Framework for Unified Representation Learning in Information Retrieval and Semantic Textual Similaritycited by 2
  31. 2025Retrieval Capabilities of Large Language Models Scale with Pretraining FLOPscited by 2
  32. 2025DiVE-k: Differential Visual Reasoning for Fine-grained Image Recognitioncited by 2
  33. 2026EgoSelf: From Memory to Personalized Egocentric Assistantcited by 2
  34. 2026Heuresis: Search Strategies for Autonomous AI Research Agents Across Quality, Diversity and Noveltycited by 2
  35. 2026Google's AI & Economy ATLAS v1.0: Mapping Gemini Usage in the Economycited by 2
  36. 2026Pandora's AI Model Routing Box: Efficient Allocation with Costly Value Estimationcited by 2
  37. 2025Predicting Reaction Time to Comprehend Scenes with Foveated Scene Understanding Mapscited by 1
  38. 2025RAGalyst: Automated Human-Aligned Agentic Evaluation for Domain-Specific RAGcited by 1

50 most cited of 94 All 94 (JSON)