Recent advances in text embedding: A Comprehensive Review of Top-Performing Methods on the MTEB Benchmark

Citations in the corpus

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation (2025, unknown): “Text representations used for retrieval include sparse count-based vectors, static word embed-dings, contextual token representations, and sentence-or passage-level embeddings [45].”
A Large-Language-Model Framework for Automated Humanitarian Situation Reporting (2025, unknown): “The emergence of large language models (LLMs) has transformed natural language processing (NLP), substantially improving performance in text classification, clustering, summarization, and question answering 5,6 .”
Open-Source Embedding Models: A Comprehensive Survey of Techniques, Benchmarks, and Applications (2026, unknown): “Benchmarks are designed to assess performance across a range of common NLP tasks, but they might not include the specific tasks or nuances of every application [76].”
Unlocking Multimodal Document Intelligence: From Current Triumphs to Future Frontiers of Visual Document Retrieval (2026, unknown): “…primary imperative is the creation of large-scale benchmarks that are not only multilingual but also multi-domain , extending into specialized corpora like legal contracts, financial reports, and medical records, which demand expert-level nuance (Tang and Yang, 2024; Cao, 2024; Chung et al., 2025).”