mlsanityData to 7 Oct 2026

Promptriever: Instruction-Trained Retrievers Can Be Prompted Like Language Models

arXiv 2409.11136 ↗First posted 17 Sep 2024cs.IR cs.CL cs.LGcited by 39

Not on the map. Why?

Abstract (arXiv)

Instruction-tuned language models (LM) are able to respond to imperative commands, providing a more natural user interface compared to their base counterparts. In this work, we present Promptriever, the first retrieval model able to be prompted like an LM. To train Promptriever, we curate and release a new instance-level instruction training set from MS MARCO, spanning nearly 500k instances. Promptriever not only achieves strong performance on standard retrieval tasks, but also follows instructions. We observe: (1) large gains (reaching SoTA) on following detailed relevance instructions (+14.3 p-MRR / +3.1 nDCG on FollowIR), (2) significantly increased robustness to lexical choices/phrasing in the query+instruction (+12.9 Robustness@10 on InstructIR), and (3) the ability to perform hyperparameter search via prompting to reliably improve retrieval performance (+1.4 average increase on BEIR). Promptriever demonstrates that retrieval models can be controlled with prompts on a per-query basis, setting the stage for future work aligning LM prompting techniques with information retrieval.

Key facts. Cited by 39 papers in the map (data through 7 Oct 2026). Builds on 39 of its 48 references that are in the map. First posted on arXiv 17 Sep 2024.

Builds on

39 of 48 references.

References · 39

  1. 2022Training language models to follow instructions with human feedbackcited by 15,712
  2. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  3. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  4. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  5. 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
  6. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,747
  7. 2022Scaling Instruction-Finetuned Language Modelscited by 2,997
  8. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,674
  9. 2016MS MARCO: A Human Generated MAchine Reading COmprehension Datasetcited by 1,591
  10. 2021Multitask Prompted Training Enables Zero-Shot Task Generalizationcited by 1,462
  11. 2021BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Modelscited by 1,225
  12. 2022Text Embeddings by Weakly-Supervised Contrastive Pre-trainingcited by 1,216
27 more
  1. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,203
  2. 2023Towards General Text Embeddings with Multi-stage Contrastive Learningcited by 705
  3. 2022MTEB: Massive Text Embedding Benchmarkcited by 623
  4. 2024OLMo: Accelerating the Science of Language Modelscited by 599
  5. 2024Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Researchcited by 475
  6. 2024LLM2Vec: Large Language Models Are Secretly Powerful Text Encoderscited by 396
  7. 2020Document Ranking with a Pretrained Sequence-to-Sequence Modelcited by 373
  8. 2022One Embedder, Any Task: Instruction-Finetuned Text Embeddingscited by 329
  9. 2023Improving Text Embeddings with Large Language Modelscited by 295
  10. 2020Overview of the TREC 2019 deep learning trackcited by 282
  11. 2023Fine-Tuning LLaMA for Multi-Stage Text Retrievalcited by 271
  12. 2022Promptagator: Few-shot Dense Retrieval From 8 Examplescited by 233
  13. 2024Generative Representational Instruction Tuningcited by 227
  14. 2023Self-Alignment with Instruction Backtranslationcited by 149
  15. 2024Nemotron-4 340B Technical Reportcited by 143
  16. 2022Task-aware Retrieval with Instructionscited by 107
  17. 2024BM25S: Orders of magnitude faster lexical search via eager sparse scoringcited by 87
  18. 2024NV-Retriever: Improving text embedding models with effective hard-negative miningcited by 83
  19. 2024Gecko: Versatile Text Embeddings Distilled from Large Language Modelscited by 81
  20. 2023InPars-v2: Large Language Models as Efficient Dataset Generators for Information Retrievalcited by 73
  21. 2024FollowIR: Evaluating and Teaching Information Retrieval Models to Follow Instructionscited by 67
  22. 2022InPars: Data Augmentation for Information Retrieval using Large Language Modelscited by 60
  23. 2024Arctic-Embed: Scalable, Efficient, and Accurate Text Embedding Modelscited by 60
  24. 2022Tevatron: An Efficient and Flexible Toolkit for Dense Retrievalcited by 47
  25. 2023"According to ...": Prompting Language Models Improves Quoting from Pre-Training Datacited by 42
  26. 2024INSTRUCTIR: A Benchmark for Instruction Following of Information Retrieval Modelscited by 32
  27. 2023NevIR: Negation in Neural Information Retrievalcited by 28

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 25; 2026: 11.

39 papers.

Sort:

By area:

  1. 2025On the Theoretical Limitations of Embedding-Based Retrievalcited by 98
  2. 2025ReasonIR: Training Retrievers for Reasoning Taskscited by 76
  3. 2025Rank1: Test-Time Compute for Reranking in Information Retrievalcited by 68
  4. 2025The Distracting Effect: Understanding Irrelevant Passages in RAGcited by 32
  5. 2025Rank-K: Test-Time Reasoning for Listwise Rerankingcited by 28
  6. 2025Diffusion vs. Autoregressive Language Models: A Text Embedding Perspectivecited by 23
  7. 2024MINTQA: A Multi-Hop Question Answering Benchmark for Evaluating LLMs on New and Tail Knowledgecited by 20
  8. 2025IFIR: A Comprehensive Benchmark for Evaluating Instruction-Following in Expert-Domain Information Retrievalcited by 16
  9. 2025O1 Embedder: Let Retrievers Think Before Actioncited by 15
  10. 2025MIR: Methodology Inspiration Retrieval for Scientific Research Problemscited by 10
  11. 2025Towards Better Instruction Following Retrieval Modelscited by 9
  12. 2025mFollowIR: a Multilingual Benchmark for Instruction Following in Retrievalcited by 7
27 more
  1. 2025Hypencoder: Hypernetworks for Information Retrievalcited by 7
  2. 2026SAGE: Benchmarking and Improving Retrieval for Deep Research Agentscited by 7
  3. 2025Don't Reinvent the Wheel: Efficient Instruction-Following Text Embedding based on Guided Space Transformationcited by 6
  4. 2025CoQuIR: A Comprehensive Benchmark for Code Quality-Aware Information Retrievalcited by 6
  5. 2025ERank: Fusing Supervised Fine-Tuning and Reinforcement Learning for Effective and Efficient Text Rerankingcited by 6
  6. 2025Benchmarking Information Retrieval Models on Complex Retrieval Taskscited by 6
  7. 2025Ranking Free RAG: Replacing Re-ranking with Selection in RAG for Sensitive Domainscited by 5
  8. 2025Exploiting Instruction-Following Retrievers for Malicious Information Retrievalcited by 4
  9. 2025Beyond Contrastive Learning: Synthetic Data Enables List-wise Training with Multiple Levels of Relevancecited by 4
  10. 2026ColBERT-Zero: To Pre-train Or Not To Pre-train ColBERT modelscited by 4
  11. 2025On The Role of Pretrained Language Models in General-Purpose Text Embeddings: A Surveycited by 3
  12. 2024RARe: Retrieval Augmented Retrieval with In-Context Examplescited by 2
  13. 2025Making Large Language Models Efficient Dense Retrieverscited by 2
  14. 2026Rethinking Reasoning-Intensive Retrieval: Evaluating and Advancing Retrievers in Agentic Search Systemscited by 2
  15. 2024Large Language Model Can Be a Foundation for Hidden Rationale-Based Retrievalcited by 1
  16. 2026REPAIR: Resolving Long-Tail Confusion in Scientific Retrievers via Fact-Verified Iterative Refinementcited by 1
  17. 2025ConceptCarve: Dynamic Realization of Evidencecited by 0
  18. 2025The Other Side of the Coin: Exploring Fairness in Retrieval-Augmented Generationcited by 0
  19. 2025MSRS: Evaluating Multi-Source Retrieval-Augmented Generationcited by 0
  20. 2025Trove: A Flexible Toolkit for Dense Retrievalcited by 0
  21. 2026Evaluating the Utility of Grounding Documents with Reference-Free LLM-based Metricscited by 0
  22. 2026Modular Expert Merging for Biomedical Retrievalcited by 0
  23. 2026Efficient Rationale-based Retrieval: On-policy Distillation from Generative Rerankers based on JEPAcited by 0
  24. 2026Hypencoder Revisited: Reproducibility and Analysis of Non-Linear Scoring for First-Stage Retrievalcited by 0
  25. 2026FollowTable: A Benchmark for Instruction-Following Table Retrievalcited by 0
  26. 2026Reproducing Complex Set-Compositional Information Retrievalcited by 0
  27. 2026The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modescited by 0