mlsanityData to 7 Oct 2026

Successive Prompting for Decomposing Complex Questions

arXiv 2212.04092 ↗First posted 8 Dec 2022cs.CLcited by 94

Not on the map. Why?

Cited by 35 in LLM reasoning, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Answering complex questions that require making latent decisions is a challenging task, especially when limited supervision is available. Recent works leverage the capabilities of large language models (LMs) to perform complex question answering in a few-shot setting by demonstrating how to output intermediate rationalizations while solving the complex question in a single pass. We introduce ``Successive Prompting'', where we iteratively break down a complex task into a simple task, solve it, and then repeat the process until we get the final solution. Successive prompting decouples the supervision for decomposing complex questions from the supervision for answering simple questions, allowing us to (1) have multiple opportunities to query in-context examples at each reasoning step (2) learn question decomposition separately from question answering, including using synthetic data, and (3) use bespoke (fine-tuned) components for reasoning steps where a large LM does not perform well. The intermediate supervision is typically manually written, which can be expensive to collect. We introduce a way to generate a synthetic dataset which can be used to bootstrap a model's ability to decompose and answer intermediate questions. Our best model (with successive prompting) achieves an improvement of ~5% absolute F1 on a few-shot version of the DROP dataset when compared with a state-of-the-art model with the same supervision.

Key facts. Cited by 94 papers in the map (data through 7 Oct 2026). Builds on 27 of its 42 references that are in the map. First posted on arXiv 8 Dec 2022.

Builds on

27 of 42 references.

References · 27

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  4. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  5. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,304
  6. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  7. 2022Least-to-Most Prompting Enables Complex Reasoning in Large Language Modelscited by 1,397
  8. 2022Measuring and Narrowing the Compositionality Gap in Language Modelscited by 1,054
  9. 2022STaR: Bootstrapping Reasoning With Reasoningcited by 895
  10. 2019DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphscited by 883
  11. 2021Show Your Work: Scratchpads for Intermediate Computation with Language Modelscited by 871
  12. 2021Learning To Retrieve Prompts for In-Context Learningcited by 641
15 more
  1. 2022Decomposed Prompting: A Modular Approach for Solving Complex Taskscited by 554
  2. 2020UnifiedQA: Crossing Format Boundaries With a Single QA Systemcited by 475
  3. 2021True Few-Shot Learning with Language Modelscited by 343
  4. 2017Don't Just Assume; Look and Answer: Overcoming Priors for Visual Question Answeringcited by 337
  5. 2021Meta-learning via Language Model In-context Tuningcited by 163
  6. 2022MRKL Systems: A modular, neuro-symbolic architecture that combines large language models, external knowledge sources and discrete reasoningcited by 153
  7. 2021Few-Shot Self-Rationalization with Natural Language Promptscited by 83
  8. 2019Neural Module Networks for Reasoning over Textcited by 65
  9. 2020Text Modular Networks: Learning to Decompose Tasks in the Language of Existing Modelscited by 65
  10. 2019Giving BERT a Calculator: Finding Operations and Arguments with Reading Comprehensioncited by 51
  11. 2019A Multi-Type Multi-Span Network for Reading Comprehension that Requires Discrete Reasoningcited by 41
  12. 2021Turning Tables: Generating Examples from Semi-structured Tables for Endowing Language Models with Reasoning Skillscited by 39
  13. 2021Contrastive Fine-tuning Improves Robustness for Neural Rankerscited by 12
  14. 2021Learning with Instance Bundles for Reading Comprehensioncited by 8
  15. 2022Counterfactual Data Augmentation improves Factuality of Abstractive Summarizationcited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 6; 2023: 37; 2024: 25; 2025: 20; 2026: 6.

94 papers.

Sort:

By area:

  1. 2023FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performancecited by 791
  2. 2023Measuring Faithfulness in Chain-of-Thought Reasoningcited by 668
  3. 2022Towards Reasoning in Large Language Models: A Surveycited by 593
  4. 2023Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Modelscited by 550
  5. 2023Augmented Language Models: a Surveycited by 398
  6. 2022Reasoning with Language Model Prompting: A Surveycited by 251
  7. 2023ToolkenGPT: Augmenting Frozen Language Models with Massive Tools via Tool Embeddingscited by 238
  8. 2023ART: Automatic multi-step reasoning and tool-use for large language modelscited by 193
  9. 2023Navigate through Enigmatic Labyrinth A Survey of Chain of Thought Reasoning: Advances, Frontiers and Futurecited by 184
  10. 2023Large Language Models are Versatile Decomposers: Decompose Evidence and Questions for Table-based Reasoningcited by 177
  11. 2024Rethinking the Bounds of LLM Reasoning: Are Multi-Agent Discussions the Key?cited by 153
  12. 2023Domain Specialization as the Key to Make Large Language Models Disruptive: A Comprehensive Surveycited by 134
38 more
  1. 2023Question Decomposition Improves the Faithfulness of Model-Generated Reasoningcited by 107
  2. 2023Branch-Solve-Merge Improves Large Language Model Evaluation and Generationcited by 104
  3. 2024DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakerscited by 91
  4. 2024If LLM Is the Wizard, Then Code Is the Wand: A Survey on How Code Empowers Large Language Models to Serve as Intelligent Agentscited by 77
  5. 2023MathChat: Converse to Tackle Challenging Math Problems with LLM Agentscited by 67
  6. 2022LAMBADA: Backward Chaining for Automated Reasoning in Natural Languagecited by 66
  7. 2024Demystifying Chains, Trees, and Graphs of Thoughtscited by 63
  8. 2022Parsel: Algorithmic Reasoning with Language Models by Composing Decompositionscited by 62
  9. 2023PEARL: Prompting Large Language Models to Plan and Execute Actions Over Long Documentscited by 61
  10. 2023Why Does ChatGPT Fall Short in Providing Truthful Answers?cited by 54
  11. 2024Improving Large Language Models via Fine-grained Reinforcement Learning with Minimum Editing Constraintcited by 39
  12. 2024MoreHopQA: More Than Multi-hop Reasoningcited by 37
  13. 2024E-SQL: Direct Schema Linking via Question Enrichment in Text-to-SQLcited by 35
  14. 2023Skills-in-Context Prompting: Unlocking Compositionality in Large Language Modelscited by 33
  15. 2024Text-Tuple-Table: Towards Information Integration in Text-to-Table Generation via Global Tuple Extractioncited by 33
  16. 2025TreeReview: A Dynamic Tree of Questions Framework for Deep and Efficient LLM-based Scientific Peer Reviewcited by 31
  17. 2023Complex Logical Reasoning over Knowledge Graphs using Large Language Modelscited by 28
  18. 2024Evaluating LLMs' Mathematical Reasoning in Financial Document Question Answeringcited by 25
  19. 2023Recursion of Thought: A Divide-and-Conquer Approach to Multi-Context Reasoning with Language Modelscited by 24
  20. 2023ThoughtSource: A central hub for large language model reasoning datacited by 23
  21. 2023Investigating Chain-of-thought with ChatGPT for Stance Detection on Social Mediacited by 23
  22. 2024On the Evaluation of Machine-Generated Reportscited by 23
  23. 2023LLM for SoC Security: A Paradigm Shiftcited by 22
  24. 2024Divide-and-Conquer Meets Consensus: Unleashing the Power of Functions in Code Generationcited by 19
  25. 2024Markov Chain of Thought for Efficient Mathematical Reasoningcited by 19
  26. 2023GEAR: Augmenting Language Models with Generalizable and Efficient Tool Resolutioncited by 17
  27. 2023Small Language Models Fine-tuned to Coordinate Larger Language Models improve Complex Reasoningcited by 16
  28. 2025CER: Confidence Enhanced Reasoning in LLMscited by 16
  29. 2025Beyond the Last Answer: Your Reasoning Trace Uncovers More than You Thinkcited by 16
  30. 2023Iterated Decomposition: Improving Science Q&A by Supervising Reasoning Processescited by 15
  31. 2024Learning Task Decomposition to Assist Humans in Competitive Programmingcited by 14
  32. 2025Speak Easy: Eliciting Harmful Jailbreaks from LLMs with Simple Interactionscited by 14
  33. 2023EchoPrompt: Instructing the Model to Rephrase Queries for Improved In-context Learningcited by 13
  34. 2025Compositional Translation: A Novel LLM-based Approach for Low-resource Machine Translationcited by 13
  35. 2024ICLEval: Evaluating In-Context Learning Ability of Large Language Modelscited by 12
  36. 2023Reasoning over Hierarchical Question Decomposition Tree for Explainable Question Answeringcited by 11
  37. 2023BLT: Can Large Language Models Handle Basic Legal Text?cited by 10
  38. 2023Few-Shot Data Synthesis for Open Domain Multi-Hop Question Answeringcited by 9

50 most cited of 94 All 94 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025SQuARE: Sequential Question Answering Reasoning Engine for Enhanced Chain-of-Thought in Large Language Models
  2. 2023In-Context Ability Transfer for Question Decomposition in Complex QA
  3. 2025One More Question is Enough, Expert Question Decomposition (EQD) Model for Domain Quantitative Reasoning
  4. 2023Self-Convinced Prompting: Few-Shot Question Answering with Repeated Introspection
  5. 2026ReasonLab: A Controlled and Auditable Evaluation of Prompting Techniques for Multiple-Choice QA
  6. 2023Synthetic Prompting: Generating Chain-of-Thought Demonstrations for Large Language Models
  7. 2024Prompting-based Synthetic Data Generation for Few-Shot Question Answering
  8. 2022Complexity-Based Prompting for Multi-Step Reasoning