mlsanityData to 14 Oct 2026

SPLADE-v3: New baselines for SPLADE

arXiv 2403.06789 ↗First posted 11 Mar 2024cs.IR cs.CLcited by 72

Not on the map. Why?

Cited by 24 in Retrieval-augmented generation, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

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.

Key facts. Cited by 72 papers in the map (data through 14 Oct 2026). Builds on 16 of its 20 references that are in the map. First posted on arXiv 11 Mar 2024.

Builds on

16 of 20 references.

References · 16

  1. 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,307
  2. 2021BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Modelscited by 1,252
  3. 2021ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interactioncited by 476
  4. 2021SPLADE: Sparse Lexical and Expansion Model for First Stage Rankingcited by 286
  5. 2021Unsupervised Corpus Aware Language Model Pre-training for Dense Passage Retrievalcited by 203
  6. 2020Improving Efficient Neural Ranking Models with Cross-Architecture Knowledge Distillationcited by 145
  7. 2021SPLADE v2: Sparse Lexical and Expansion Model for Information Retrievalcited by 127
  8. 2022From Distillation to Hard Negative Sampling: Making Sparse Neural IR Models More Effectivecited by 98
  9. 2020Distilling Dense Representations for Ranking using Tightly-Coupled Teacherscited by 52
  10. 2022Tevatron: An Efficient and Flexible Toolkit for Dense Retrievalcited by 47
  11. 2022Curriculum Learning for Dense Retrieval Distillationcited by 38
  12. 2021Simplified Data Wrangling with ir_datasetscited by 27
4 more
  1. 2022An Efficiency Study for SPLADE Modelscited by 26
  2. 2023Benchmarking Middle-Trained Language Models for Neural Searchcited by 4
  3. 2023The tale of two MS MARCO -- and their unfair comparisonscited by 3
  4. 2023Ranger: A Toolkit for Effect-Size Based Multi-Task Evaluationcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 9; 2025: 25; 2026: 38.

72 papers.

Sort:

By area:

  1. 2024A Survey on Retrieval-Augmented Text Generation for Large Language Modelscited by 77
  2. 2024Ragnar"ok: A Reusable RAG Framework and Baselines for TREC 2024 Retrieval-Augmented Generation Trackcited by 32
  3. 2025Rank-K: Test-Time Reasoning for Listwise Rerankingcited by 29
  4. 2024Context Embeddings for Efficient Answer Generation in RAGcited by 26
  5. 2025PeerQA: A Scientific Question Answering Dataset from Peer Reviewscited by 22
  6. 2024RetroLLM: Empowering Large Language Models to Retrieve Fine-grained Evidence within Generationcited by 20
  7. 2025PISCO: Pretty Simple Compression for Retrieval-Augmented Generationcited by 20
  8. 2024JaColBERTv2.5: Optimising Multi-Vector Retrievers to Create State-of-the-Art Japanese Retrievers with Constrained Resourcescited by 15
  9. 2025CSPLADE: Learned Sparse Retrieval with Causal Language Modelscited by 10
  10. 2024DiSCo: LLM Knowledge Distillation for Efficient Sparse Retrieval in Conversational Searchcited by 9
  11. 2024Mistral-SPLADE: LLMs for better Learned Sparse Retrievalcited by 8
  12. 2024rerankers: A Lightweight Python Library to Unify Ranking Methodscited by 8
38 more
  1. 2024Towards Competitive Search Relevance For Inference-Free Learned Sparse Retrieverscited by 8
  2. 2025Decoding Dense Embeddings: Sparse Autoencoders for Interpreting and Discretizing Dense Retrievalcited by 8
  3. 2026Revisiting Text Ranking in Deep Researchcited by 7
  4. 2025Enhancing Lexicon-Based Text Embeddings with Large Language Modelscited by 6
  5. 2026Learning Retrieval Models with Sparse Autoencoderscited by 6
  6. 2026LACONIC: Dense-Level Effectiveness for Scalable Sparse Retrieval via a Two-Phase Training Curriculumcited by 5
  7. 2025OSCAR: Online Soft Compression And Rerankingcited by 4
  8. 2025Balancing the Blend: An Experimental Analysis of Trade-offs in Hybrid Searchcited by 4
  9. 2025LEAF: Knowledge Distillation of Text Embedding Models with Teacher-Aligned Representationscited by 4
  10. 2025Dense Retrieval for Low Resource Languages -- the Case of Amharic Languagecited by 3
  11. 2025An Alternative to FLOPS Regularization to Effectively Productionize SPLADE-Doccited by 3
  12. 2026Overview of the TREC 2025 Retrieval Augmented Generation (RAG) Trackcited by 3
  13. 2025Towards Lossless Token Pruning in Late-Interaction Retrieval Modelscited by 2
  14. 2025CLIRudit: Cross-Lingual Information Retrieval of Scientific Documentscited by 2
  15. 2025Med-R3: Enhancing Medical Retrieval-Augmented Reasoning of LLMs via Progressive Reinforcement Learningcited by 2
  16. 2025Simple Projection Variants Improve ColBERT Performancecited by 2
  17. 2026LANCER: LLM Reranking for Nugget Coveragecited by 2
  18. 2026Scaling Laws for Embedding Dimension in Information Retrievalcited by 2
  19. 2026UEmbed: Unified Sparse and Dense Multimodal Embeddingscited by 2
  20. 2025HEISIR: Hierarchical Expansion of Inverted Semantic Indexing for Training-free Retrieval of Conversational Data using LLMscited by 1
  21. 2025LightRetriever: A LLM-based Text Retrieval Architecture with Extremely Faster Query Inferencecited by 1
  22. 2025DiffLoRA: Differential Low-Rank Adapters for Large Language Modelscited by 1
  23. 2025Adaptive Personalized Conversational Information Retrievalcited by 1
  24. 2025Lighting the Way for BRIGHT: Reproducible Baselines with Anserini, Pyserini, and RankLLMcited by 1
  25. 2025Efficient Sketching and Nearest Neighbor Search Algorithms for Sparse Vector Setscited by 1
  26. 2026RoutIR: Fast Serving of Retrieval Pipelines for Retrieval-Augmented Generationcited by 1
  27. 2026Beyond Relevance: On the Relationship Between Retrieval and RAG Information Coveragecited by 1
  28. 2026Empirical Evaluation of PDF Parsing and Chunking for Financial Question Answering with RAGcited by 1
  29. 2026Efficient Multivector Retrieval with Token-Aware Clustering and Hierarchical Indexingcited by 1
  30. 2026Uncertainty-Aware Hybrid Retrieval for Long-Document RAGcited by 1
  31. 2026Tevatron Meets Megatron: Expert-Parallel LLM Reranker Training on an Academic Budgetcited by 1
  32. 2026Less can be More: Relieving RAG Bottlenecks via Evidence Frontloading and Pressure-Adaptive Budgetingcited by 1
  33. 2025Improving Document Retrieval Coherence for Semantically Equivalent Queriescited by 0
  34. 2025ABCD-LINK: Annotation Bootstrapping for Cross-Document Fine-Grained Linkscited by 0
  35. 2025REGENT: Relevance-Guided Attention for Entity-Aware Multi-Vector Neural Re-Rankingcited by 0
  36. 2025Breaking the Curse of Dimensionality: On the Stability of Modern Vector Retrievalcited by 0
  37. 2026Reasoning by Commented Code for Table Question Answeringcited by 0
  38. 2026Where Does Robustness Live? Neuron-Guided Adaptation for Retrieval-Augmented Language Modelscited by 0

50 most cited of 72 All 72 (JSON)