NanoBEIR
PulseAugur coverage of NanoBEIR — every cluster mentioning NanoBEIR across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
Hugging Face trains embedding models for efficient retrieval
Hugging Face has introduced a new training technique called Token Pooling-Aware Training designed to make multi-vector embedding models more efficient. This method addresses the issue of large storage requirements for t…
-
arXiv papers tackle long document retrieval with new chunking and hybrid strategies
Two new arXiv papers explore advanced methods for improving retrieval from long documents. The first paper, "Calibrating Document-Local Boundaries for Contextual Chunk Retrieval," introduces a framework to adapt discrim…
-
LLM preference generation and calibration research shows model discordance and improved methods
Recent research explores the reliability and calibration of Large Language Model (LLM) generated preferences. One study found that while LLMs exhibit self-coherence in preferences, significant discordance exists across …