M3-Embedding is a single model for multi-lingual, multi-functional, and multi-granular text embeddings trained via self-knowledge distillation that achieves new state-of-the-art results on multilingual, cross-lingual, and long-document retrieval benchmarks.
hub
Hall, Daniel Cer, and Yinfei Yang
12 Pith papers cite this work. Polarity classification is still indexing.
12
Pith papers citing it
hub tools
citation-role summary
background 1
method 1
citation-polarity summary
representative citing papers
GloRank reformulates list-wise reranking as token generation over a global item identifier space, using supervised pre-training followed by reinforcement learning to maximize list-wise utility and outperforming baselines on benchmarks and industrial data.
SA²CRQ uses sequential adaptive residual quantization based on path entropy plus anchored curriculum regularization from head items to improve both efficiency and cold-start performance in generative retrieval.
Nomic AI produced and open-sourced a reproducible 8192-context English text embedder that exceeds OpenAI Ada-002 and text-embedding-3-small performance on MTEB short-context and LoCo long-context benchmarks.
Informativeness and diversity of samples selected by active learning show no correlation with test performance on translation tasks using few samples; ordering and pre-training effects dominate instead.
Search-R3 trains LLMs to output search embeddings as a direct product of step-by-step reasoning via supervised pre-training and a specialized RL environment that avoids full corpus re-encoding.
Open-source multilingual E5 embedding models are trained via contrastive pre-training on 1 billion text pairs and fine-tuning, with an instruction-tuned model matching English SOTA performance.
Data-CUBE applies a two-level curriculum (TSP-based task ordering via simulated annealing plus difficulty-sorted mini-batches) to multi-task instruction tuning and reports gains on MTEB sentence representation tasks.
GTE_base is a compact text embedding model using multi-stage contrastive learning on diverse data that outperforms OpenAI's API and 10x larger models on massive benchmarks and works for code as text.
Mira-Embeddings-V1 adapts embeddings for recruitment reranking by synthesizing positive and hard-negative samples with LLMs, then applies JD-JD contrastive and JD-CV triplet training plus a BoundaryHead MLP, lifting Recall@50 from 68.89% to 77.55% and Recall@200 from 0.5969 to 0.7047.
citing papers explorer
-
From Local Indices to Global Identifiers: Generative Reranking for Recommender Systems via Global Action Space
GloRank reformulates list-wise reranking as token generation over a global item identifier space, using supervised pre-training followed by reinforcement learning to maximize list-wise utility and outperforming baselines on benchmarks and industrial data.