4 papers
Flash-GMM: A Memory-Efficient Kernel for Scalable Soft Clustering
Gal Bloch, Ariel Gera, Matan Orbach +2
We present \textbf{Flash-GMM}, a fused Triton kernel for efficient computation of Gaussian Mixture Models (GMMs) over large-scale data in a single GPU pass. By eliminating the need…
Task-Adaptive Embedding Refinement via Test-time LLM Guidance
Ariel Gera, Shir Ashury-Tahan, Gal Bloch +2
We explore the effectiveness of an LLM-guided query refinement paradigm for extending the usability of embedding models to challenging zero-shot search and classification tasks. Ou…
An Analysis of Hyper-Parameter Optimization Methods for Retrieval Augmented Generation
Matan Orbach, Ohad Eytan, Benjamin Sznajder +12
Optimizing Retrieval-Augmented Generation (RAG) configurations for specific tasks is a complex and resource-intensive challenge. Motivated by this challenge, frameworks for RAG hyp…
Statistical multi-metric evaluation and visualization of LLM system predictive performance
Samuel Ackerman, Eitan Farchi, Orna Raz +1
The evaluation of generative or discriminative large language model (LLM)-based systems is often a complex multi-dimensional problem. Typically, a set of system configuration alter…