mlsanityData to 7 Oct 2026

Task-aware Retrieval with Instructions

arXiv 2211.09260 ↗First posted 16 Nov 2022cs.CLcited by 107

Not on the map. Why?

Abstract (arXiv)

We study the problem of retrieval with instructions, where users of a retrieval system explicitly describe their intent along with their queries. We aim to develop a general-purpose task-aware retrieval system using multi-task instruction tuning, which can follow human-written instructions to find the best documents for a given query. We introduce the first large-scale collection of approximately 40 retrieval datasets with instructions, BERRI, and present TART, a multi-task retrieval system trained on BERRI with instructions. TART shows strong capabilities to adapt to a new retrieval task via instructions and advances the state of the art on two zero-shot retrieval benchmarks, BEIR and LOTTE, outperforming models up to three times larger. We further introduce a new evaluation setup, X^2-Retrieval to better reflect real-world scenarios, where diverse domains and tasks are pooled and a system needs to find documents aligning users' intents. In this setup, TART significantly outperforms competitive baselines, further demonstrating the effectiveness of guiding retrieval with instructions.

Key facts. Cited by 107 papers in the map (data through 7 Oct 2026). Builds on 64 of its 100 references that are in the map. First posted on arXiv 16 Nov 2022.

Builds on

64 of 100 references.

References · 64

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2022Training language models to follow instructions with human feedbackcited by 15,712
  3. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  4. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,115
  5. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  6. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,747
  7. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  8. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,895
  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. 2015Microsoft COCO Captions: Data Collection and Evaluation Servercited by 1,447
  12. 2018FEVER: a large-scale dataset for Fact Extraction and VERificationcited by 1,362
38 more
  1. 2018Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarizationcited by 1,308
  2. 2017Get To The Point: Summarization with Pointer-Generator Networkscited by 1,281
  3. 2019PubMedQA: A Dataset for Biomedical Research Question Answeringcited by 1,271
  4. 2021BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Modelscited by 1,225
  5. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,203
  6. 2020ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERTcited by 1,160
  7. 2022Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Taskscited by 858
  8. 2021Cross-Task Generalization via Natural Language Crowdsourcing Instructionscited by 696
  9. 2019Latent Retrieval for Weakly Supervised Open Domain Question Answeringcited by 691
  10. 2019CodeSearchNet Challenge: Evaluating the State of Semantic Code Searchcited by 638
  11. 2019Passage Re-ranking with BERTcited by 629
  12. 2020KILT: a Benchmark for Knowledge Intensive Language Taskscited by 571
  13. 2019ELI5: Long Form Question Answeringcited by 567
  14. 2020Fact or Fiction: Verifying Scientific Claimscited by 546
  15. 2018Wizard of Wikipedia: Knowledge-Powered Conversational agentscited by 530
  16. 2022MedMCQA : A Large-scale Multi-Subject Multi-Choice Dataset for Medical domain Question Answeringcited by 525
  17. 2021ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interactioncited by 464
  18. 2021Large Dual Encoders Are Generalizable Retrieverscited by 454
  19. 2021MetaICL: Learning to Learn In Contextcited by 450
  20. 2020SPECTER: Document-level Representation Learning using Citation-informed Transformerscited by 426
  21. 2020RocketQA: An Optimized Training Approach to Dense Passage Retrieval for Open-Domain Question Answeringcited by 410
  22. 2015A Neural Attention Model for Abstractive Sentence Summarizationcited by 394
  23. 2020AmbigQA: Answering Ambiguous Open-domain Questionscited by 385
  24. 2020Document Ranking with a Pretrained Sequence-to-Sequence Modelcited by 373
  25. 2022PromptSource: An Integrated Development Environment and Repository for Natural Language Promptscited by 288
  26. 2020Pretrained Transformers for Text Ranking: BERT and Beyondcited by 266
  27. 2021Efficiently Teaching an Effective Dense Retriever with Balanced Topic Aware Samplingcited by 238
  28. 2022Promptagator: Few-shot Dense Retrieval From 8 Examplescited by 233
  29. 2019Document Expansion by Query Predictioncited by 225
  30. 2017SearchQA: A New Q&A Dataset Augmented with Context from a Search Enginecited by 221
  31. 2022SGPT: GPT Sentence Embeddings for Semantic Searchcited by 204
  32. 2018WikiHow: A Large Scale Text Summarization Datasetcited by 203
  33. 2018ReCoRD: Bridging the Gap between Human and Machine Commonsense Reading Comprehensioncited by 198
  34. 2021PAQ: 65 Million Probably-Asked Questions and What You Can Do With Themcited by 198
  35. 2020CLIMATE-FEVER: A Dataset for Verification of Real-World Climate Claimscited by 195
  36. 2022Improving Passage Retrieval with Zero-Shot Question Generationcited by 164
  37. 2021Optimizing Dense Retrieval Model Training with Hard Negativescited by 154
  38. 2020Open-Domain Question Answering Goes Conversational via Question Rewritingcited by 147

50 most cited of 64 All 64 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 28; 2024: 40; 2025: 21; 2026: 16.

107 papers.

Sort:

By area:

  1. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,800
  2. 2023Towards General Text Embeddings with Multi-stage Contrastive Learningcited by 705
  3. 2022Precise Zero-Shot Dense Retrieval without Relevance Labelscited by 508
  4. 2024NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Modelscited by 466
  5. 2023Augmented Language Models: a Surveycited by 398
  6. 2024LLM2Vec: Large Language Models Are Secretly Powerful Text Encoderscited by 396
  7. 2023Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agentscited by 356
  8. 2023Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergycited by 343
  9. 2023Large Language Models for Information Retrieval: A Surveycited by 331
  10. 2022One Embedder, Any Task: Instruction-Finetuned Text Embeddingscited by 329
  11. 2023Large Language Models are Effective Text Rankers with Pairwise Ranking Promptingcited by 302
  12. 2023MIMIC-IT: Multi-Modal In-Context Instruction Tuningcited by 264
38 more
  1. 2024Generative Representational Instruction Tuningcited by 227
  2. 2024VLM2Vec: Training Vision-Language Models for Massive Multimodal Embedding Taskscited by 222
  3. 2024Hallucination-Free? Assessing the Reliability of Leading AI Legal Research Toolscited by 170
  4. 2023Recommendation as Instruction Following: A Large Language Model Empowered Recommendation Approachcited by 168
  5. 2023UniIR: Training and Benchmarking Universal Multimodal Information Retrieverscited by 165
  6. 2024MM-Embed: Universal Multimodal Retrieval with Multimodal LLMscited by 159
  7. 2024BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrievalcited by 153
  8. 2024MagicLens: Self-Supervised Image Retrieval with Open-Ended Instructionscited by 119
  9. 2023How to Train Your DRAGON: Diverse Augmentation Towards Generalizable Dense Retrievalcited by 116
  10. 2024CodeRAG-Bench: Can Retrieval Augment Code Generation?cited by 89
  11. 2024MegaPairs: Massive Data Synthesis For Universal Multimodal Retrievalcited by 84
  12. 2024Gecko: Versatile Text Embeddings Distilled from Large Language Modelscited by 81
  13. 2023Exploring the Benefits of Training Expert Language Models over Instruction Tuningcited by 80
  14. 2024Reliable, Adaptable, and Attributable Language Models with Retrievalcited by 73
  15. 2023Augmentation-Adapted Retriever Improves Generalization of Language Models as Generic Plug-Incited by 71
  16. 2024In-context Learning with Retrieved Demonstrations for Language Models: A Surveycited by 69
  17. 2025Rank1: Test-Time Compute for Reranking in Information Retrievalcited by 68
  18. 2024FollowIR: Evaluating and Teaching Information Retrieval Models to Follow Instructionscited by 67
  19. 2024Promptriever: Instruction-Trained Retrievers Can Be Prompted Like Language Modelscited by 39
  20. 2024BMRetriever: Tuning Large Language Models as Better Biomedical Text Retrieverscited by 38
  21. 2023UDAPDR: Unsupervised Domain Adaptation via LLM Prompting and Distillation of Rerankerscited by 37
  22. 2024RAR-b: Reasoning as Retrieval Benchmarkcited by 33
  23. 2024INSTRUCTIR: A Benchmark for Instruction Following of Information Retrieval Modelscited by 32
  24. 2023PDFTriage: Question Answering over Long, Structured Documentscited by 29
  25. 2024AutoRAG: Automated Framework for optimization of Retrieval Augmented Generation Pipelinecited by 26
  26. 2023Large Language Models are Strong Zero-Shot Retrievercited by 25
  27. 2023IfQA: A Dataset for Open-domain Question Answering under Counterfactual Presuppositionscited by 25
  28. 2023When do Generative Query and Document Expansions Fail? A Comprehensive Study Across Methods, Retrievers, and Datasetscited by 25
  29. 2024Long Context RAG Performance of Large Language Modelscited by 23
  30. 2023Prompt-Guided Retrieval Augmentation for Non-Knowledge-Intensive Taskscited by 21
  31. 2024Recent advances in text embedding: A Comprehensive Review of Top-Performing Methods on the MTEB Benchmarkcited by 19
  32. 2025DRAMA: Diverse Augmentation from Large Language Models to Smaller Dense Retrieverscited by 19
  33. 2023GAR-meets-RAG Paradigm for Zero-Shot Information Retrievalcited by 18
  34. 2024ChatRetriever: Adapting Large Language Models for Generalized and Robust Conversational Dense Retrievalcited by 18
  35. 2023Pre-training Multi-task Contrastive Learning Models for Scientific Literature Understandingcited by 16
  36. 2025IFIR: A Comprehensive Benchmark for Evaluating Instruction-Following in Expert-Domain Information Retrievalcited by 16
  37. 2024BIRCO: A Benchmark of Information Retrieval Tasks with Complex Objectivescited by 15
  38. 2024Meta-Task Prompting Elicits Embeddings from Large Language Modelscited by 15

50 most cited of 107 All 107 (JSON)