PulseAugur
EN
LIVE 20:03:04
ENTITY Splade

Splade

PulseAugur coverage of Splade — every cluster mentioning Splade across labs, papers, and developer communities, ranked by signal.

Show in brief
Total · 30d
7
21 over 90d
Releases · 30d
0
0 over 90d
Papers · 30d
6
18 over 90d
TIER MIX · 90D
TOPICS
SENTIMENT · 30D

1 day(s) with sentiment data

RECENT · PAGE 1/2 · 22 TOTAL
  1. TOOL · CL_348766 ·

    SPARSEUP training recipe boosts sparse retrieval models to new benchmark highs

    Researchers have developed SPARSEUP, a new training methodology for learned sparse retrieval models that improves their efficiency and effectiveness. This approach addresses the challenges in training these models by op…

  2. TOOL · CL_345136 ·

    Small SPLADE model outperforms large embedding models in RAG

    A new, small-scale model called SPLADE has demonstrated superior performance compared to larger 8B embedding models for Retrieval-Augmented Generation (RAG) systems. Developed by the user, the SPLADE model, specifically…

  3. RESEARCH · CL_317029 ·

    Research paper reveals 'fusion tax' in hybrid AI retrieval methods

    A new research paper titled "The Fusion Tax" analyzes the drawbacks of hybrid retrieval methods, which combine sparse and dense retrieval techniques. The study found that while hybrid retrieval often shows aggregate gai…

  4. TOOL · CL_317032 ·

    New GRIP system challenges graph-based search for learned sparse retrieval

    Researchers have developed a new graph-based approximate nearest neighbor (ANN) system for learned sparse retrieval (LSR) called GRIP. This system challenges the prevailing notion that inverted indexes are superior to g…

  5. RESEARCH · CL_301542 ·

    New research explores LLM integration with sparse retrieval systems

    Two new research papers explore methods for improving large language model (LLM) integration with sparse retrieval systems. The first paper, "Aligning LLMs with Sparse Retrieval via Adaptive Sparse Supervision," propose…

  6. TOOL · CL_298464 ·

    New research explores faithful query resolution for conversational search

    A new paper from arXiv explores the balance between query fidelity and retrieval breadth in conversational search systems. Researchers evaluated five query-generation configurations using BM25 and SPLADE retrieval withi…

  7. TOOL · CL_284900 ·

    RAGFlip paper measures negative flips in retriever upgrades

    A new research paper, RAGFlip, introduces a method for evaluating retriever upgrades by focusing on query-level negative flips. These flips occur when a new retriever fails to find a relevant passage that a previous ret…

  8. TOOL · CL_239391 ·

    University of Aveiro team details BioASQ 14B biomedical QA system

    The BIT.UA team from the University of Aveiro has detailed their participation in the BioASQ 14B challenge, focusing on biomedical question answering. They implemented a modular system that refactored both retrieval and…

  9. RESEARCH · CL_205628 ·

    New research explores static pruning and LLM-based query expansion for retrieval systems

    Two new research papers explore methods to improve information retrieval systems. The first paper, "Static Pruning Across Sparse Retrieval Regimes," investigates how static pruning techniques can be applied across diffe…

  10. TOOL · CL_168087 ·

    BM25, Dense Retrieval, and SPLADE: Choosing RAG retrieval methods

    A technical article compares three primary retrieval methods for Retrieval-Augmented Generation (RAG) projects: BM25, Dense Retrieval, and SPLADE. BM25 is a fast, CPU-based keyword-matching algorithm, while Dense Retrie…

  11. TOOL · CL_156436 ·

    New SIFT system enables self-improving document classification

    A new self-improving classification system called SIFT (Self-Improving, Frozen-gate Training) has been developed to address the challenges of dynamic document classification in enterprise settings. SIFT utilizes a cost-…

  12. RESEARCH · CL_131684 ·

    New theory explains late-interaction retrieval models, introduces Signed MaxSim

    Researchers have theoretically quantified the representational power of late-interaction retrieval models, specifically those using the MaxSim similarity function. The study demonstrates that MaxSim can precisely replic…

  13. TOOL · CL_111510 ·

    GPUSparse system accelerates learned sparse retrieval using GPU parallelization

    Researchers have developed GPUSparse, a novel system designed to accelerate learned sparse retrieval models by leveraging GPU parallelization. This system addresses the CPU-bound bottleneck in current sparse retrieval m…

  14. RESEARCH · CL_105011 ·

    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…

  15. RESEARCH · CL_97776 ·

    New technique improves SPLADE retrieval models with larger encoders

    Researchers have identified a performance degradation issue when using larger, more powerful pretrained encoders with SPLADE, a neural sparse retrieval model. This problem, termed a "scale mismatch" in the MLM head, can…

  16. TOOL · CL_85050 ·

    Spring AI and Pgvector enable native hybrid search in PostgreSQL

    This article details how to implement native hybrid search within PostgreSQL using the pgvector extension and Spring AI. It advocates for consolidating search functionalities into a single database, eliminating the need…

  17. TOOL · CL_65900 ·

    New SAE-SPLADE model enhances information retrieval with semantic concepts

    Researchers have developed a new model called SAE-SPLADE that enhances information retrieval by replacing traditional vocabulary backbones with a latent space of semantic concepts learned via Sparse Auto-Encoders. This …

  18. RESEARCH · CL_58714 ·

    New method extracts BM25-ready sparse features from dense retrieval models

    Researchers have introduced a new method called Latent Terms, which demonstrates that dense retrieval models can be decomposed into sparse features suitable for traditional BM25 scoring. This technique, applied to froze…

  19. TOOL · CL_49291 ·

    SPLADE model's 'wacky weights' analyzed for interpretability

    Researchers have conducted a systematic investigation into "wacky weights" within SPLADE, a learned sparse retrieval model. These weights, which assign importance to expansion terms that seem semantically unrelated to t…

  20. TOOL · CL_15918 ·

    Expanded-SPLADE models show limitations in retrieval fine-tuning

    This paper investigates the impact of different pre-training datasets and methods on the performance of Expanded-SPLADE (ESPLADE) models for neural information retrieval. The study found that models pre-trained on gener…