Splade
PulseAugur coverage of Splade — every cluster mentioning Splade across labs, papers, and developer communities, ranked by signal.
5 day(s) with sentiment data
-
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…
-
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 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…
-
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…
-
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 …
-
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…
-
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…
-
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…
-
Towards Universal Tabular Embeddings: A Benchmark Across Data Tasks
Researchers have developed two new frameworks for improving tabular data processing. One, called "Improving Robustness of Tabular Retrieval via Representational Stability," addresses the issue of serialization sensitivi…
-
From Tokens to Concepts: Leveraging SAE for SPLADE
Researchers have developed a new model called SAE-SPLADE that replaces the traditional vocabulary backbone of Sparse Information Retrieval (IR) models like SPLADE with a latent space of semantic concepts. This approach,…