mlsanityData to 7 Oct 2026

Automatic Prompt Augmentation and Selection with Chain-of-Thought from Labeled Data

arXiv 2302.12822 ↗First posted 24 Feb 2023cs.CLcited by 119

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

Abstract (arXiv)

Chain-of-thought (CoT) advances the reasoning abilities of large language models (LLMs) and achieves superior performance in complex reasoning tasks. However, most CoT studies rely on carefully designed human-annotated rational chains to prompt LLMs, posing challenges for real-world applications where labeled data is available without rational chains. This paper proposes a new strategy, Automate-CoT (Automatic Prompt Augmentation and Selection with Chain-of-Thought), that can bypass human engineering of CoT by automatically augmenting rational chains from a small labeled dataset, and then pruning low-quality chains to construct a candidate pool of machine-generated rationale chains based on the labels. Finally, it selects the optimal combination of several rationale chains from the pool for CoT prompting by employing a variance-reduced policy gradient strategy to estimate the significance of each example. Automate-CoT enables a quick adaptation of the CoT technique to different tasks. Experimental results demonstrate the effectiveness of our method, where competitive results are achieved on arithmetic reasoning (+2.7%), commonsense reasoning (+3.4%), symbolic reasoning (+3.2%), and non-reasoning tasks (+2.5%). The code is available at https://github.com/SHUMKASHUN/Automate-CoT.

Key facts. Cited by 119 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 64 of its 81 references that are in the map. First posted on arXiv 24 Feb 2023.

Builds on

64 of 81 references.

Closest ancestors · 4

Same direction, newest first

  1. 2022Automatic Chain of Thought Prompting in Large Language Models7 Oct
  2. 2022Complexity-Based Prompting for Multi-Step Reasoning3 Oct
  3. 2022Large Language Models are Zero-Shot Reasoners24 May
  4. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Models21 Mar

Other references · 60

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2022Training language models to follow instructions with human feedbackcited by 15,712
  4. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  5. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  6. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  7. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  8. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,304
  9. 2021Prefix-Tuning: Optimizing Continuous Prompts for Generationcited by 3,878
  10. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,769
  11. 2022Emergent Abilities of Large Language Modelscited by 2,483
  12. 2020DeBERTa: Decoding-enhanced BERT with Disentangled Attentioncited by 2,157
38 more
  1. 2018Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answeringcited by 2,114
  2. 2022Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language modelscited by 1,970
  3. 2018CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledgecited by 1,793
  4. 2021Calibrate Before Use: Improving Few-Shot Performance of Language Modelscited by 1,371
  5. 2020Making Pre-trained Language Models Better Few-shot Learnerscited by 1,255
  6. 2021What Makes Good In-Context Examples for GPT-3?cited by 1,184
  7. 2021Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivitycited by 1,122
  8. 2019How Can We Know What Language Models Know?cited by 953
  9. 2022STaR: Bootstrapping Reasoning With Reasoningcited by 895
  10. 2021Are NLP Models really able to Solve Simple Math Word Problems?cited by 861
  11. 2021Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategiescited by 736
  12. 2021BARTScore: Evaluating Generated Text as Text Generationcited by 719
  13. 2021GPT Understands, Toocited by 715
  14. 2019Universal Adversarial Triggers for Attacking and Analyzing NLPcited by 709
  15. 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 682
  16. 2022Large Language Models Can Self-Improvecited by 656
  17. 2019MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalismscited by 653
  18. 2017Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problemscited by 642
  19. 2018Black-box Adversarial Attacks with Limited Queries and Informationcited by 499
  20. 2018e-SNLI: Natural Language Inference with Natural Language Explanationscited by 468
  21. 2021Learning How to Ask: Querying LMs with Mixtures of Soft Promptscited by 376
  22. 2022Dynamic Prompt Learning via Policy Gradient for Semi-structured Mathematical Reasoningcited by 347
  23. 2021A Diverse Corpus for Evaluating and Developing English Math Word Problem Solverscited by 314
  24. 2021Factual Probing Is [MASK]: Learning vs. Learning to Recallcited by 291
  25. 2022Black-Box Tuning for Language-Model-as-a-Servicecited by 254
  26. 2022Can language models learn from explanations in context?cited by 248
  27. 2022Selective Annotation Makes Language Models Better Few-Shot Learnerscited by 242
  28. 2021PTR: Prompt Tuning with Rules for Text Classificationcited by 238
  29. 2021WARP: Word-level Adversarial ReProgrammingcited by 220
  30. 2022Active Example Selection for In-Context Learningcited by 195
  31. 2019Commonsense Knowledge Mining from Pretrained Modelscited by 189
  32. 2018Prior Convictions: Black-Box Adversarial Attacks with Bandits and Priorscited by 145
  33. 2022GrIPS: Gradient-free, Edit-based Instruction Search for Prompting Large Language Modelscited by 127
  34. 2019Improving Black-box Adversarial Attacks with a Transfer-based Priorcited by 121
  35. 2022Rationale-Augmented Ensembles in Language Modelscited by 111
  36. 2021BERTese: Learning to Speak to BERTcited by 82
  37. 2022Black-box Prompt Learning for Pre-trained Language Modelscited by 70
  38. 2021PADA: Example-based Prompt Learning for on-the-fly Adaptation to Unseen Domainscited by 61

50 most cited of 60 All 60 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 29; 2024: 52; 2025: 30; 2026: 8.

119 papers.

Sort:

By area:

  1. 2023Graph of Thoughts: Solving Elaborate Problems with Large Language Modelscited by 873
  2. 2023Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolutioncited by 521
  3. 2023Navigate through Enigmatic Labyrinth A Survey of Chain of Thought Reasoning: Advances, Frontiers and Futurecited by 184
  4. 2024MapCoder: Multi-Agent Code Generation for Competitive Problem Solvingcited by 177
  5. 2024A Survey on Recent Advances in LLM-Based Multi-turn Dialogue Systemscited by 170
  6. 2023DetGPT: Detect What You Need via Reasoningcited by 112
  7. 2023Large Language Models as Analogical Reasonerscited by 107
  8. 2024LISA: Layerwise Importance Sampling for Memory-Efficient Large Language Model Fine-Tuningcited by 88
  9. 2023Unleashing the potential of prompt engineering for large language modelscited by 72
  10. 2023Igniting Language Intelligence: The Hitchhiker's Guide From Chain-of-Thought Reasoning to Language Agentscited by 72
  11. 2024Retrieval Augmented Generation (RAG) and Beyond: A Comprehensive Survey on How to Make your LLMs use External Data More Wiselycited by 65
  12. 2024GroupDebate: Enhancing the Efficiency of Multi-Agent Debate Using Group Discussioncited by 64
38 more
  1. 2023Cue-CoT: Chain-of-thought Prompting for Responding to In-depth Dialogue Questions with LLMscited by 62
  2. 2023Towards Better Chain-of-Thought Prompting Strategies: A Surveycited by 62
  3. 2024Unlocking the Capabilities of Thought: A Reasoning Boundary Framework to Quantify and Optimize Chain-of-Thoughtcited by 56
  4. 2023SAMAug: Point Prompt Augmentation for Segment Anything Modelcited by 38
  5. 2023Which Examples to Annotate for In-Context Learning? Towards Effective and Efficient Selectioncited by 36
  6. 2025Fino1: On the Transferability of Reasoning-Enhanced LLMs and Reinforcement Learning to Financecited by 32
  7. 2025CODESIM: Multi-Agent Code Generation and Problem Solving through Simulation-Driven Planning and Debuggingcited by 31
  8. 2024Data Augmentation using Large Language Models: Data Perspectives, Learning Paradigms and Challengescited by 30
  9. 2024Meteor: Mamba-based Traversal of Rationale for Large Language and Vision Modelscited by 30
  10. 2023CodeCoT: Tackling Code Syntax Errors in CoT Reasoning for Code Generationcited by 29
  11. 2023Balancing Autonomy and Alignment: A Multi-Dimensional Taxonomy for Autonomous LLM-powered Multi-Agent Architecturescited by 25
  12. 2023Mathematical Language Models: A Surveycited by 24
  13. 2024Logic-of-Thought: Injecting Logic into Contexts for Full Reasoning in Large Language Modelscited by 23
  14. 2025Back Attention: Understanding and Enhancing Multi-Hop Reasoning in Large Language Modelscited by 23
  15. 2025ShadowCoT: Cognitive Hijacking for Stealthy Reasoning Backdoors in LLMscited by 23
  16. 2024Why Solving Multi-agent Path Finding with Large Language Model has not Succeeded Yetcited by 22
  17. 2025S2-MAD: Breaking the Token Barrier to Enhance Multi-Agent Debate Efficiencycited by 21
  18. 2025Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuningcited by 19
  19. 2023Just Ask One More Time! Self-Agreement Improves Reasoning of Language Models in (Almost) All Scenarioscited by 18
  20. 2024SwarmBrain: Embodied agent for real-time strategy game StarCraft II via large language modelscited by 18
  21. 2024Enhancing Code Generation Performance of Smaller Models by Distilling the Reasoning Ability of LLMscited by 17
  22. 2023Enhancing Chain-of-Thoughts Prompting with Iterative Bootstrapping in Large Language Modelscited by 16
  23. 2025AdaReasoner: Adaptive Reasoning Enables More Flexible Thinking in Large Language Modelscited by 16
  24. 2023LyricWhiz: Robust Multilingual Zero-shot Lyrics Transcription by Whispering to ChatGPTcited by 15
  25. 2024Can We Verify Step by Step for Incorrect Answer Detection?cited by 15
  26. 2023A Survey on Stability of Learning with Limited Labelled Data and its Sensitivity to the Effects of Randomnesscited by 14
  27. 2024EPIC: Effective Prompting for Imbalanced-Class Data Synthesis in Tabular Data Classification via Large Language Modelscited by 14
  28. 2024Large Language Models: A New Approach for Privacy Policy Analysis at Scalecited by 14
  29. 2025HyperTree Planning: Enhancing LLM Reasoning via Hierarchical Thinkingcited by 14
  30. 2025CulFiT: A Fine-grained Cultural-aware LLM Training Paradigm via Multilingual Critique Data Synthesiscited by 14
  31. 2023StrategyLLM: Large Language Models as Strategy Generators, Executors, Optimizers, and Evaluators for Problem Solvingcited by 13
  32. 2024Distilling Reasoning Ability from Large Language Models with Adaptive Thinkingcited by 13
  33. 2024DEEM: Dynamic Experienced Expert Modeling for Stance Detectioncited by 12
  34. 2024Efficient Prompting for LLM-based Generative Internet of Thingscited by 12
  35. 2024ICLEval: Evaluating In-Context Learning Ability of Large Language Modelscited by 12
  36. 2024CoPS: Empowering LLM Agents with Provable Cross-Task Experience Sharingcited by 12
  37. 2024Does DetectGPT Fully Utilize Perturbation? Bridging Selective Perturbation to Fine-tuned Contrastive Learning Detector would be Bettercited by 11
  38. 2024FIRST: Teach A Reliable Large Language Model Through Efficient Trustworthy Distillationcited by 11

50 most cited of 119 All 119 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Scaling Code-Assisted Chain-of-Thoughts and Instructions for Model Reasoning
  2. 2024ChainLM: Empowering Large Language Models with Improved Chain-of-Thought Prompting
  3. 2024To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning
  4. 2024Break the Chain: Large Language Models Can be Shortcut Reasoners
  5. 2022Towards Understanding Chain-of-Thought Prompting: An Empirical Study of What Matters
  6. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
  7. 2024Unveiling the Statistical Foundations of Chain-of-Thought Prompting Methods
  8. 2023Boosting Language Models Reasoning with Chain-of-Knowledge Prompting