mlsanityData to 14 Oct 2026

InPars-v2: Large Language Models as Efficient Dataset Generators for Information Retrieval

arXiv 2301.01820 ↗First posted 4 Jan 2023cs.IR cs.AIcited by 73

Not on the map. Why?

Abstract (arXiv)

Recently, InPars introduced a method to efficiently use large language models (LLMs) in information retrieval tasks: via few-shot examples, an LLM is induced to generate relevant queries for documents. These synthetic query-document pairs can then be used to train a retriever. However, InPars and, more recently, Promptagator, rely on proprietary LLMs such as GPT-3 and FLAN to generate such datasets. In this work we introduce InPars-v2, a dataset generator that uses open-source LLMs and existing powerful rerankers to select synthetic query-document pairs for training. A simple BM25 retrieval pipeline followed by a monoT5 reranker finetuned on InPars-v2 data achieves new state-of-the-art results on the BEIR benchmark. To allow researchers to further improve our method, we open source the code, synthetic data, and finetuned models: https://github.com/zetaalphavector/inPars/tree/master/tpu

Key facts. Cited by 73 papers in the map (data through 14 Oct 2026). Builds on 8 of its 10 references that are in the map. First posted on arXiv 4 Jan 2023.

Builds on

8 of 10 references.

References · 8

  1. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,780
  2. 2021BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Modelscited by 1,252
  3. 2018Adafactor: Adaptive Learning Rates with Sublinear Memory Costcited by 905
  4. 2020Document Ranking with a Pretrained Sequence-to-Sequence Modelcited by 376
  5. 2022Promptagator: Few-shot Dense Retrieval From 8 Examplescited by 235
  6. 2022RankT5: Fine-Tuning T5 for Text Ranking with Ranking Lossescited by 115
  7. 2022InPars: Data Augmentation for Information Retrieval using Large Language Modelscited by 62
  8. 2021Pyserini: An Easy-to-Use Python Toolkit to Support Replicable IR Research with Sparse and Dense Representationscited by 60

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 27; 2024: 21; 2025: 18; 2026: 7.

73 papers.

Sort:

By area:

  1. 2023Large Language Models for Information Retrieval: A Surveycited by 331
  2. 2024A Survey on Knowledge Distillation of Large Language Modelscited by 284
  3. 2025Gemini Embedding: Generalizable Embeddings from Geminicited by 94
  4. 2024Gecko: Versatile Text Embeddings Distilled from Large Language Modelscited by 83
  5. 2023HAGRID: A Human-LLM Collaborative Dataset for Generative Information-Seeking with Attributioncited by 56
  6. 2023LLatrieval: LLM-Verified Retrieval for Verifiable Generationcited by 52
  7. 2023Open-source Large Language Models are Strong Zero-shot Query Likelihood Models for Document Rankingcited by 44
  8. 2024Promptriever: Instruction-Trained Retrievers Can Be Prompted Like Language Modelscited by 40
  9. 2023UDAPDR: Unsupervised Domain Adaptation via LLM Prompting and Distillation of Rerankerscited by 37
  10. 2023Using Large Language Models to Generate, Validate, and Apply User Intent Taxonomiescited by 34
  11. 2024LLMs are Also Effective Embedding Models: An In-depth Overviewcited by 32
  12. 2023Large Language Model Augmented Narrative Driven Recommendationscited by 31
38 more
  1. 2023CLARA: Classifying and Disambiguating User Commands for Reliable Interactive Robotic Agentscited by 30
  2. 2023Information Retrieval Meets Large Language Models: A Strategic Report from Chinese IR Communitycited by 29
  3. 2024Understand What LLM Needs: Dual Preference Alignment for Retrieval-Augmented Generationcited by 27
  4. 2023Large Language Models are Strong Zero-Shot Retrievercited by 26
  5. 2023When do Generative Query and Document Expansions Fail? A Comprehensive Study Across Methods, Retrievers, and Datasetscited by 26
  6. 2023Leveraging LLMs for Synthesizing Training Data Across Many Languages in Multilingual Dense Retrievalcited by 24
  7. 2024Towards Trustworthy AI: A Review of Ethical and Robust Large Language Modelscited by 22
  8. 2024I Think, Therefore I am: Benchmarking Awareness of Large Language Models Using AwareBenchcited by 21
  9. 2024Linq-Embed-Mistral Technical Reportcited by 20
  10. 2024Recent advances in text embedding: A Comprehensive Review of Top-Performing Methods on the MTEB Benchmarkcited by 19
  11. 2023GAR-meets-RAG Paradigm for Zero-Shot Information Retrievalcited by 18
  12. 2023Enhancing Large Language Models for Secure Code Generation: A Dataset-driven Study on Vulnerability Mitigationcited by 15
  13. 2023An Interdisciplinary Outlook on Large Language Models for Scientific Researchcited by 15
  14. 2023InPars-Light: Cost-Effective Unsupervised Training of Efficient Rankerscited by 14
  15. 2023Rank-without-GPT: Building GPT-Independent Listwise Rerankers on Open-Source Large Language Modelscited by 14
  16. 2023Adapting Large Language Models for Education: Foundational Capabilities, Potentials, and Challengescited by 13
  17. 2023Soft Prompt Tuning for Augmenting Dense Retrieval with Large Language Modelscited by 12
  18. 2024AIR-Bench: Automated Heterogeneous Information Retrieval Benchmarkcited by 12
  19. 2024Evaluating RAG-Fusion with RAGElo: an Automated Elo-based Frameworkcited by 11
  20. 2024Little Giants: Synthesizing High-Quality Embedding Data at Scalecited by 11
  21. 2025ASRank: Zero-Shot Re-Ranking with Answer Scent for Document Retrievalcited by 9
  22. 2024DreamStruct: Understanding Slides and User Interfaces via Synthetic Data Generationcited by 8
  23. 2023cTBLS: Augmenting Large Language Models with Conversational Tablescited by 7
  24. 2023Selecting which Dense Retriever to use for Zero-Shot Searchcited by 7
  25. 2024Generalized Contrastive Learning for Multi-Modal Retrieval and Rankingcited by 7
  26. 2024AGENT-CQ: Automatic Generation and Evaluation of Clarifying Questions for Conversational Search with LLMscited by 7
  27. 2025Improving Scientific Document Retrieval with Concept Coverage-based Query Set Generationcited by 7
  28. 2024DUQGen: Effective Unsupervised Domain Adaptation of Neural Rankers by Diversifying Synthetic Query Generationcited by 5
  29. 2025On Synthetic Data Strategies for Domain-Specific Generative Retrievalcited by 5
  30. 2025ChEmbed: Enhancing Chemical Literature Search Through Domain-Specific Text Embeddingscited by 5
  31. 2025MTEB-NL and E5-NL: Embedding Benchmark and Models for Dutchcited by 5
  32. 2023Simple Yet Effective Neural Ranking and Reranking Baselines for Cross-Lingual Information Retrievalcited by 4
  33. 2024Self-Retrieval: End-to-End Information Retrieval with One Large Language Modelcited by 4
  34. 2024Do Audio-Language Models Understand Linguistic Variations?cited by 4
  35. 2025Beyond Contrastive Learning: Synthetic Data Enables List-wise Training with Multiple Levels of Relevancecited by 4
  36. 2023MT4CrossOIE: Multi-stage Tuning for Cross-lingual Open Information Extractioncited by 3
  37. 2024Zero-Shot Dense Retrieval with Embeddings from Relevance Feedbackcited by 3
  38. 2025On The Role of Pretrained Language Models in General-Purpose Text Embeddings: A Surveycited by 3

50 most cited of 73 All 73 (JSON)