mlsanityData to 7 Oct 2026

Internet-augmented language models through few-shot prompting for open-domain question answering

arXiv 2203.05115 ↗First posted 10 Mar 2022cs.CL cs.LGcited by 131

Not on the map. Why?

Cited by 32 in LLM reasoning, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

In this work, we aim to capitalize on the unique few-shot capabilities of large-scale language models (LSLMs) to overcome some of their challenges with respect to grounding to factual and up-to-date information. Motivated by semi-parametric language models (LMs), which ground their decisions in external retrieved evidence, we use few-shot prompting to learn to condition LMs on information returned from the web using Google Search, a broad and constantly updated knowledge source. Our approach does not involve fine-tuning or learning additional parameters, thus making it applicable to any LM, offering therefore a strong baseline. Indeed, we find that LMs conditioned on the web surpass performance of closed-book models of similar, or even larger, model sizes in open-domain question answering. Finally, we find that increasing the inference-time compute of models, achieved via using multiple retrieved evidences to generate multiple answers followed by a reranking stage that uses scores generated by the same LMs, leads to better performance and alleviates lower performance of smaller few-shot LMs. All in all, our findings suggest that it might be beneficial to slow down the race towards the biggest model and instead shift attention towards finding more effective ways to use models, including but not limited to, better prompting or increasing inference-time compute.

Key facts. Cited by 131 papers in the map (data through 7 Oct 2026). Builds on 38 of its 51 references that are in the map. First posted on arXiv 10 Mar 2022.

Builds on

38 of 51 references.

References · 38

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  3. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  4. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  5. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,747
  6. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  7. 2021Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processingcited by 2,222
  8. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
  9. 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,722
  10. 2018FEVER: a large-scale dataset for Fact Extraction and VERificationcited by 1,362
  11. 2021Improving language models by retrieving from trillions of tokenscited by 1,278
  12. 2021BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Modelscited by 1,225
26 more
  1. 2022LaMDA: Language Models for Dialog Applicationscited by 1,218
  2. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,203
  3. 2021Scaling Language Models: Methods, Analysis & Insights from Training Gophercited by 1,199
  4. 2021What Makes Good In-Context Examples for GPT-3?cited by 1,184
  5. 2020On Faithfulness and Factuality in Abstractive Summarizationcited by 895
  6. 2019Generalization through Memorization: Nearest Neighbor Language Modelscited by 788
  7. 2021Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategiescited by 736
  8. 2021Retrieval Augmentation Reduces Hallucination in Conversationcited by 691
  9. 2021Learning To Retrieve Prompts for In-Context Learningcited by 641
  10. 2021Entity-Based Knowledge Conflicts in Question Answeringcited by 349
  11. 2021Internet-Augmented Dialogue Generationcited by 217
  12. 2018Fast Lexically Constrained Decoding with Dynamic Beam Allocation for Neural Machine Translationcited by 181
  13. 2019MultiFC: A Real-World Multi-Domain Dataset for Evidence-Based Fact Checking of Claimscited by 169
  14. 2020Answering Complex Open-Domain Questions with Multi-Hop Dense Retrievalcited by 160
  15. 2021NeuroLogic A*esque Decoding: Constrained Text Generation with Lookahead Heuristicscited by 153
  16. 2021SituatedQA: Incorporating Extra-Linguistic Contexts into QAcited by 145
  17. 2021End-to-End Training of Multi-Document Reader and Retriever for Open-Domain Question Answeringcited by 133
  18. 2019Multi-hop Reading Comprehension through Question Decomposition and Rescoringcited by 119
  19. 2020Unsupervised Question Decomposition for Question Answeringcited by 118
  20. 2019On NMT Search Errors and Model Errors: Cat Got Your Tongue?cited by 114
  21. 2021Adaptive Semiparametric Language Modelscited by 83
  22. 2021The Web Is Your Oyster - Knowledge-Intensive NLP against a Very Large Web Corpuscited by 60
  23. 2020Generating Fact Checking Briefscited by 50
  24. 2021R2-D2: A Modular Baseline for Open-Domain Question Answeringcited by 37
  25. 2021Boosting Search Engines with Interactive Agentscited by 19
  26. 2021A Multi-Level Attention Model for Evidence-Based Fact Checkingcited by 13

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 18; 2023: 47; 2024: 36; 2025: 21; 2026: 9.

131 papers.

Sort:

By area:

  1. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  2. 2023A Survey of Large Language Modelscited by 2,537
  3. 2023Gorilla: Large Language Model Connected with Massive APIscited by 1,302
  4. 2022WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agentscited by 1,197
  5. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 940
  6. 2022Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learningcited by 886
  7. 2023DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelinescited by 803
  8. 2023Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Modelscited by 695
  9. 2023A Comprehensive Overview of Large Language Modelscited by 639
  10. 2022Improving alignment of dialogue agents via targeted human judgementscited by 527
  11. 2023LLM+P: Empowering Large Language Models with Optimal Planning Proficiencycited by 496
  12. 2024A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Modelscited by 450
38 more
  1. 2023Augmented Language Models: a Surveycited by 398
  2. 2022Complexity-Based Prompting for Multi-Step Reasoningcited by 387
  3. 2023Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedbackcited by 351
  4. 2022Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoningcited by 331
  5. 2023Large Language Models for Information Retrieval: A Surveycited by 331
  6. 2022Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLPcited by 316
  7. 2023FreshLLMs: Refreshing Large Language Models with Search Engine Augmentationcited by 308
  8. 2023Tool Learning with Foundation Modelscited by 302
  9. 2022Generate rather than Retrieve: Large Language Models are Strong Context Generatorscited by 296
  10. 2022Teaching language models to support answers with verified quotescited by 290
  11. 2024RAFT: Adapting Language Model to Domain Specific RAGcited by 258
  12. 2023GPT4Tools: Teaching Large Language Model to Use Tools via Self-instructioncited by 245
  13. 2024Tool Learning with Large Language Models: A Surveycited by 221
  14. 2023MetaTool Benchmark for Large Language Models: Deciding Whether to Use Tools and Which to Usecited by 209
  15. 2024RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMscited by 200
  16. 2022Can large language models reason about medical questions?cited by 194
  17. 2023TaskMatrix.AI: Completing Tasks by Connecting Foundation Models with Millions of APIscited by 184
  18. 2023Chain-of-Note: Enhancing Robustness in Retrieval-Augmented Language Modelscited by 180
  19. 2023ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Modelscited by 174
  20. 2023Foundation Models for Decision Making: Problems, Methods, and Opportunitiescited by 160
  21. 2023Evaluating Correctness and Faithfulness of Instruction-Following Models for Question Answeringcited by 150
  22. 2023Progressive-Hint Prompting Improves Reasoning in Large Language Modelscited by 147
  23. 2025Dynamic Cheatsheet: Test-Time Learning with Adaptive Memorycited by 146
  24. 2022Autoregressive Search Engines: Generating Substrings as Document Identifierscited by 112
  25. 2025A Survey of Graph Retrieval-Augmented Generation for Customized Large Language Modelscited by 85
  26. 2023Cognitive Mirage: A Review of Hallucinations in Large Language Modelscited by 83
  27. 2023Context-faithful Prompting for Large Language Modelscited by 76
  28. 2023Unleashing the potential of prompt engineering for large language modelscited by 72
  29. 2024Retrieval-Augmented Generation for Natural Language Processing: A Surveycited by 70
  30. 2025OctoTools: An Agentic Framework with Extensible Tools for Complex Reasoningcited by 69
  31. 2024SuRe: Summarizing Retrievals using Answer Candidates for Open-domain QA of LLMscited by 67
  32. 2025Nemotron-Research-Tool-N1: Exploring Tool-Using Language Models with Reinforced Reasoningcited by 67
  33. 2023Tool Documentation Enables Zero-Shot Tool-Usage with Large Language Modelscited by 66
  34. 2022Recitation-Augmented Language Modelscited by 65
  35. 2024What Are Tools Anyway? A Survey from the Language Model Perspectivecited by 53
  36. 2024Don't Trust: Verify -- Grounding LLM Quantitative Reasoning with Autoformalizationcited by 53
  37. 2025When to use Graphs in RAG: A Comprehensive Analysis for Graph Retrieval-Augmented Generationcited by 46
  38. 2023Knowledge-Augmented Large Language Models for Personalized Contextual Query Suggestioncited by 43

50 most cited of 131 All 131 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024Prompting-based Synthetic Data Generation for Few-Shot Question Answering
  2. 2023Few-Shot Data Synthesis for Open Domain Multi-Hop Question Answering
  3. 2025Rethinking Data: Towards Better Performing Domain-Specific Small Language Models
  4. 2024Teaching Smaller Language Models To Generalise To Unseen Compositional Questions (Full Thesis)
  5. 2023MinPrompt: Graph-based Minimal Prompt Data Augmentation for Few-shot Question Answering
  6. 2023Self-Convinced Prompting: Few-Shot Question Answering with Repeated Introspection
  7. 2026Gradually Excavating External Knowledge for Implicit Complex Question Answering
  8. 2023DIVKNOWQA: Assessing the Reasoning Ability of LLMs via Open-Domain Question Answering over Knowledge Base and Text