mlsanityData to 7 Oct 2026

Iteratively Prompt Pre-trained Language Models for Chain of Thought

arXiv 2203.08383 ↗First posted 16 Mar 2022cs.CLcited by 75

On the map: LLM reasoning → Prompting and chain-of-thought reasoning

Abstract (arXiv)

While Pre-trained Language Models (PLMs) internalize a great amount of world knowledge, they have been shown incapable of recalling these knowledge to solve tasks requiring complex & multi-step reasoning. Similar to how humans develop a "chain of thought" for these tasks, how can we equip PLMs with such abilities? In this work, we explore an iterative prompting framework, a new prompting paradigm which progressively elicits relevant knowledge from PLMs for multi-step inference. We identify key limitations of existing prompting methods, namely they are either restricted to queries with a single identifiable relation/predicate, or being agnostic to input contexts, which makes it difficult to capture variabilities across different inference steps. We propose an iterative context-aware prompter, which addresses these limitations by learning to dynamically synthesize prompts conditioned on the current step's contexts. Experiments on three datasets involving multi-step reasoning show the effectiveness of the iterative scheme and the context-aware prompter design.

Key facts. Cited by 75 papers in the map (data through 7 Oct 2026). Placed in Prompting and chain-of-thought reasoning, one of 17 directions in LLM reasoning. Builds on 33 of its 50 references that are in the map. First posted on arXiv 16 Mar 2022.

Builds on

33 of 50 references.

Closest ancestors · 1

Same direction, newest first

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Models28 Jan

Other references · 32

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  3. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  4. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
  5. 2021Prefix-Tuning: Optimizing Continuous Prompts for Generationcited by 3,878
  6. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,769
  7. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  8. 2021Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processingcited by 2,222
  9. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
  10. 2019Language Models as Knowledge Bases?cited by 1,922
  11. 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,259
  12. 2021Scaling Language Models: Methods, Analysis & Insights from Training Gophercited by 1,199
20 more
  1. 2019How Can We Know What Language Models Know?cited by 953
  2. 2020A Primer in BERTology: What we know about how BERT workscited by 807
  3. 2021Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategiescited by 736
  4. 2020How Much Knowledge Can You Pack Into the Parameters of a Language Model?cited by 713
  5. 2019Designing and Interpreting Probes with Control Taskscited by 608
  6. 2021Learning How to Ask: Querying LMs with Mixtures of Soft Promptscited by 376
  7. 2019A Multiscale Visualization of Attention in the Transformer Modelcited by 292
  8. 2021Factual Probing Is [MASK]: Learning vs. Learning to Recallcited by 291
  9. 2021Reframing Instructional Prompts to GPTk's Languagecited by 176
  10. 2019oLMpics -- On what Language Model Pre-training Capturescited by 161
  11. 2020Unsupervised Commonsense Question Answering with Self-Talkcited by 161
  12. 2020Answering Complex Open-Domain Questions with Multi-Hop Dense Retrievalcited by 160
  13. 2020Question and Answer Test-Train Overlap in Open-Domain Question Answering Datasetscited by 137
  14. 2021Baleen: Robust Multi-Hop Reasoning at Scale via Condensed Retrievalcited by 63
  15. 2021Can Generative Pre-trained Language Models Serve as Knowledge Bases for Closed-book QA?cited by 62
  16. 2019Answering Complex Open-domain Questions Through Iterative Query Generationcited by 60
  17. 2020Language Models as Fact Checkers?cited by 51
  18. 2021Prompting Contrastive Explanations for Commonsense Reasoning Taskscited by 45
  19. 2019R4C: A Benchmark for Evaluating RC Systems to Get the Right Answer for the Right Reasoncited by 36
  20. 2021Towards Transparent Interactive Semantic Parsing via Step-by-Step Correctioncited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 4; 2023: 31; 2024: 22; 2025: 13; 2026: 5.

75 papers.

Sort:

By area:

  1. 2023A Survey of Large Language Modelscited by 2,537
  2. 2023Multimodal Chain-of-Thought Reasoning in Language Modelscited by 740
  3. 2022A Survey on In-context Learningcited by 717
  4. 2022Towards Reasoning in Large Language Models: A Surveycited by 593
  5. 2023MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuningcited by 483
  6. 2023Augmented Language Models: a Surveycited by 398
  7. 2022Reasoning with Language Model Prompting: A Surveycited by 251
  8. 2023Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual Taskscited by 243
  9. 2024Chain of Agents: Large Language Models Collaborating on Long-Context Taskscited by 201
  10. 2023Navigate through Enigmatic Labyrinth A Survey of Chain of Thought Reasoning: Advances, Frontiers and Futurecited by 184
  11. 2024AmpleGCG: Learning a Universal and Transferable Generative Model of Adversarial Suffixes for Jailbreaking Both Open and Closed LLMscited by 160
  12. 2023Task Contamination: Language Models May Not Be Few-Shot Anymorecited by 98
38 more
  1. 2023A Theory of Emergent In-Context Learning as Implicit Structure Inductioncited by 86
  2. 2023NPHardEval: Dynamic Benchmark on Reasoning Ability of Large Language Models via Complexity Classescited by 78
  3. 2024Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalizationcited by 78
  4. 2022LAMBADA: Backward Chaining for Automated Reasoning in Natural Languagecited by 66
  5. 2023Towards Better Chain-of-Thought Prompting Strategies: A Surveycited by 62
  6. 2023Prompted LLMs as Chatbot Modules for Long Open-domain Conversationcited by 61
  7. 2023T-SciQ: Teaching Multimodal Chain-of-Thought Reasoning via Mixed Large Language Model Signals for Science Question Answeringcited by 59
  8. 2023DERA: Enhancing Large Language Model Completions with Dialog-Enabled Resolving Agentscited by 52
  9. 2023Self-Verification Improves Few-Shot Clinical Information Extractioncited by 52
  10. 2023OpenICL: An Open-Source Framework for In-context Learningcited by 51
  11. 2023BoardgameQA: A Dataset for Natural Language Reasoning with Contradictory Informationcited by 42
  12. 2023Are Large Language Models Ready for Healthcare? A Comparative Study on Clinical Language Understandingcited by 40
  13. 2024SciInstruct: a Self-Reflective Instruction Annotated Dataset for Training Scientific Language Modelscited by 38
  14. 2024Prompting Techniques for Secure Code Generation: A Systematic Investigationcited by 33
  15. 2023IDEAL: Influence-Driven Selective Annotations Empower In-Context Learners in Large Language Modelscited by 26
  16. 2024Leveraging LLM Reasoning Enhances Personalized Recommender Systemscited by 26
  17. 2023Robust Visual Question Answering: Datasets, Methods, and Future Challengescited by 23
  18. 2025Creativity in LLM-based Multi-Agent Systems: A Surveycited by 23
  19. 2024Markov Chain of Thought for Efficient Mathematical Reasoningcited by 19
  20. 2023Tree Prompting: Efficient Task Adaptation without Fine-Tuningcited by 17
  21. 2023Designing LLM Chains by Adapting Techniques from Crowdsourcing Workflowscited by 17
  22. 2024The "Colonial Impulse" of Natural Language Processing: An Audit of Bengali Sentiment Analysis Tools and Their Identity-based Biasescited by 16
  23. 2023GROVE: A Retrieval-augmented Complex Story Generation Framework with A Forest of Evidencecited by 14
  24. 2024Hierarchical Retrieval-Augmented Generation Model with Rethink for Multi-hop Question Answeringcited by 14
  25. 2023Explaining Competitive-Level Programming Solutions using LLMscited by 13
  26. 2025RAIDEN-R1: Improving Role-awareness of LLMs via GRPO with Verifiable Rewardcited by 13
  27. 2023Aladdin: Zero-Shot Hallucination of Stylized 3D Assets from Abstract Scene Descriptionscited by 11
  28. 2023The Iron(ic) Melting Pot: Reviewing Human Evaluation in Humour, Irony and Sarcasm Generationcited by 11
  29. 2025Compositional Generalization from Learned Skills via CoT Training: A Theoretical and Structural Analysis for Reasoningcited by 10
  30. 2024On-the-fly Definition Augmentation of LLMs for Biomedical NERcited by 9
  31. 2023Predicting the Quality of Revisions in Argumentative Writingcited by 7
  32. 2024An Empirical Categorization of Prompting Techniques for Large Language Models: A Practitioner's Guidecited by 7
  33. 2024SADL: An Effective In-Context Learning Method for Compositional Visual QAcited by 5
  34. 2024Exploring Prompt Engineering: A Systematic Review with SWOT Analysiscited by 5
  35. 2023Beyond Traditional Teaching: The Potential of Large Language Models and Chatbots in Graduate Engineering Educationcited by 4
  36. 2023KwaiYiiMath: Technical Reportcited by 4
  37. 2024Promptly Predicting Structures: The Return of Inferencecited by 4
  38. 2024Prompting Explicit and Implicit Knowledge for Multi-hop Question Answering Based on Human Reading Processcited by 4

50 most cited of 75 All 75 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024Enhancing Chain of Thought Prompting in Large Language Models via Reasoning Patterns
  2. 2026Beyond the Prompt in Large Language Models: Comprehension, In-Context Learning, and Chain-of-Thought
  3. 2024Unveiling the Statistical Foundations of Chain-of-Thought Prompting Methods
  4. 2023Enhancing Chain-of-Thoughts Prompting with Iterative Bootstrapping in Large Language Models
  5. 2026Diverge to Induce Prompting: Multi-Rationale Induction for Zero-Shot Reasoning
  6. 2023An automatically discovered chain-of-thought prompt generalizes to novel models and datasets
  7. 2023R3 Prompting: Review, Rephrase and Resolve for Chain-of-Thought Reasoning in Large Language Models under Noisy Context
  8. 2023Metacognitive Prompting Improves Understanding in Large Language Models