Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

SPLADE-v3: New baselines for SPLADE

About

A companion to the release of the latest version of the SPLADE library. We describe changes to the training structure and present our latest series of models -- SPLADE-v3. We compare this new version to BM25, SPLADE++, as well as re-rankers, and showcase its effectiveness via a meta-analysis over more than 40 query sets. SPLADE-v3 further pushes the limit of SPLADE models: it is statistically significantly more effective than both BM25 and SPLADE++, while comparing well to cross-encoder re-rankers. Specifically, it gets more than 40 MRR@10 on the MS MARCO dev set, and improves by 2% the out-of-domain results on the BEIR benchmark.

Carlos Lassance, Herv\'e D\'ejean, Thibault Formal, St\'ephane Clinchant• 2024

Related benchmarks

TaskDatasetResultRank
Text-to-motion generationHumanML3D (test)
FID0.033
331
Text-to-motion generationKIT-ML (test)
FID0.143
115
RetrievalMS MARCO (dev)
MRR@100.387
84
RetrievalTREC DL 2019
NDCG@1075.2
71
Information RetrievalNFCorpus (test)
NDCG@100.348
65
Information RetrievalSciFact (test)
NDCG@100.688
65
Information RetrievalBEIR--
59
Information RetrievalMS Marco--
56
Information RetrievalSCIDOCS (test)
NDCG@1015.2
16
Information RetrievalFEVER (test)
NDCG@100.796
9
Showing 10 of 23 rows

Other info

Code

Follow for update