MMTEB: Massive Multilingual Text Embedding Benchmark
PulseAugur coverage of MMTEB: Massive Multilingual Text Embedding Benchmark — every cluster mentioning MMTEB: Massive Multilingual Text Embedding Benchmark across labs, papers, and developer communities, ranked by signal.
3 day(s) with sentiment data
-
BITEMBED framework offers extreme low-bit text embeddings for LLMs
Researchers have developed BITEMBED, a novel framework for creating highly efficient text embeddings using LLMs. This approach converts pre-trained LLM backbones into embedding encoders with ternary weights and quantize…
-
HAKARI-Bench offers lightweight evaluation for retrieval models · 2 sources tracked
Researchers have introduced HAKARI-Bench, a lightweight benchmark designed to streamline the evaluation of retrieval architectures and efficiency settings for retrieval-augmented generation and semantic search. This new…
-
New method corrects mean bias in text embeddings
Researchers have identified a consistent bias in current text embedding models, where each embedding can be decomposed into a sentence-specific component and a near-identical mean component across all sentences. They pr…