MTEB

MTEB is a benchmark used to evaluate the performance of text embedding methods, specifically in the context of large language models.

Papers using MTEB (6)

Let LLMs Speak Embedding Languages: Generative Text Embeddings via Iterative Contrastive Refinement2025 · 5 citesPromptEmbedder: Efficient and Transferable Text Embedding via Dual-LLM Soft Prompting2026ReverseEOL: Improving Training-free Text Embeddings via Text Reversal in Decoder-only LLMs2026KV-Embedding: Training-free Text Embedding via Internal KV Re-routing in Decoder-only LLMs2026GEM: Empowering LLM for both Embedding Generation and Language Understanding2025GenEOL: Harnessing the Generative Power of LLMs for Training-Free Sentence Embeddings2024