mlsanityData to 7 Oct 2026

Large Language Models as Analogical Reasoners

arXiv 2310.01714 ↗First posted 3 Oct 2023cs.LGcited by 107

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

Abstract (arXiv)

Chain-of-thought (CoT) prompting for language models demonstrates impressive performance across reasoning tasks, but typically needs labeled exemplars of the reasoning process. In this work, we introduce a new prompting approach, analogical prompting, designed to automatically guide the reasoning process of large language models. Inspired by analogical reasoning, a cognitive process in which humans draw from relevant past experiences to tackle new problems, our approach prompts language models to self-generate relevant exemplars or knowledge in the context, before proceeding to solve the given problem. This method presents several advantages: it obviates the need for labeling or retrieving exemplars, offering generality and convenience; it can also tailor the generated exemplars and knowledge to each problem, offering adaptability. Experimental results show that our approach outperforms 0-shot CoT and manual few-shot CoT in a variety of reasoning tasks, including math problem solving in GSM8K and MATH, code generation in Codeforces, and other reasoning tasks in BIG-Bench.

Key facts. Cited by 107 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 70 of its 135 references that are in the map. First posted on arXiv 3 Oct 2023.

Builds on

70 of 135 references.

Closest ancestors · 9

Same direction, newest first

  1. 2023Automatic Prompt Augmentation and Selection with Chain-of-Thought from Labeled Data24 Feb
  2. 2022Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks22 Nov
  3. 2022Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them17 Oct
  4. 2022Automatic Chain of Thought Prompting in Large Language Models7 Oct
  5. 2022Large Language Models are Zero-Shot Reasoners24 May
  6. 2022Maieutic Prompting: Logically Consistent Reasoning with Recursive Explanations24 May
  7. 2022Least-to-Most Prompting Enables Complex Reasoning in Large Language Models21 May
  8. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Models21 Mar
  9. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Models28 Jan

Other references · 61

  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. 2023GPT-4 Technical Reportcited by 18,132
  4. 2022Training language models to follow instructions with human feedbackcited by 15,712
  5. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  6. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  7. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  8. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  9. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,203
  10. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  11. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,747
  12. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
38 more
  1. 2021Program Synthesis with Large Language Modelscited by 3,509
  2. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,500
  3. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,155
  4. 2022Scaling Instruction-Finetuned Language Modelscited by 2,997
  5. 2020The Pile: An 800GB Dataset of Diverse Text for Language Modelingcited by 2,346
  6. 2022Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language modelscited by 1,970
  7. 2018CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledgecited by 1,793
  8. 2022Competition-Level Code Generation with AlphaCodecited by 1,427
  9. 2021What Makes Good In-Context Examples for GPT-3?cited by 1,184
  10. 2023PaLM 2 Technical Reportcited by 1,154
  11. 2018Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Taskcited by 1,120
  12. 2022Measuring and Narrowing the Compositionality Gap in Language Modelscited by 1,054
  13. 2023Teaching Large Language Models to Self-Debugcited by 963
  14. 2019How Can We Know What Language Models Know?cited by 953
  15. 2019DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphscited by 883
  16. 2021Measuring Coding Challenge Competence With APPScited by 879
  17. 2023Reasoning with Language Model is Planning with World Modelcited by 846
  18. 2023REPLUG: Retrieval-Augmented Black-Box Language Modelscited by 786
  19. 2021Cross-Task Generalization via Natural Language Crowdsourcing Instructionscited by 696
  20. 2022Decomposed Prompting: A Modular Approach for Solving Complex Taskscited by 554
  21. 2023Is ChatGPT a General-Purpose Natural Language Processing Task Solver?cited by 486
  22. 2023Med-Flamingo: a Multimodal Medical Few-shot Learnercited by 387
  23. 2021QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answeringcited by 386
  24. 2023Language Models can Solve Computer Taskscited by 371
  25. 2022Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLPcited by 316
  26. 2023Large Language Models as Tool Makerscited by 293
  27. 2022Selective Annotation Makes Language Models Better Few-Shot Learnerscited by 242
  28. 2022Emergent Analogical Reasoning in Large Language Modelscited by 239
  29. 2022Data Contamination: From Memorization to Exploitationcited by 234
  30. 2022UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Modelscited by 231
  31. 2022Binding Language Models in Symbolic Languagescited by 224
  32. 2019KagNet: Knowledge-Aware Graph Networks for Commonsense Reasoningcited by 216
  33. 2022LinkBERT: Pretraining Language Models with Document Linkscited by 209
  34. 2019SPoC: Search-based Pseudocode to Codecited by 176
  35. 2022GreaseLM: Graph REASoning Enhanced Language Models for Question Answeringcited by 170
  36. 2023Solving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-Verificationcited by 166
  37. 2022Deep Bidirectional Language-Knowledge Graph Pretrainingcited by 156
  38. 2022Retrieval-Augmented Multimodal Language Modelingcited by 125

50 most cited of 61 All 61 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 40; 2025: 49; 2026: 15.

107 papers.

Sort:

By area:

  1. 2024LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Codecited by 1,906
  2. 2024Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researcherscited by 348
  3. 2024Chain-of-Thought Reasoning Without Promptingcited by 208
  4. 2024MapCoder: Multi-Agent Code Generation for Competitive Problem Solvingcited by 177
  5. 2023LINC: A Neurosymbolic Approach for Logical Reasoning by Combining Language Models with First-Order Logic Proverscited by 161
  6. 2024Self-Discover: Large Language Models Self-Compose Reasoning Structurescited by 108
  7. 2024Buffer of Thoughts: Thought-Augmented Reasoning with Large Language Modelscited by 91
  8. 2025Atom of Thoughts for Markov LLM Test-Time Scalingcited by 54
  9. 2024A Survey of Prompt Engineering Methods in Large Language Models for Different NLP Taskscited by 46
  10. 2024Process-Driven Autoformalization in Lean 4cited by 45
  11. 2025The Homogenizing Effect of Large Language Models on Human Expression and Thoughtcited by 35
  12. 2024ReGAL: Refactoring Programs to Discover Generalizable Abstractionscited by 32
38 more
  1. 2025Generative to Agentic AI: Survey, Conceptualization, and Challengescited by 32
  2. 2025CODESIM: Multi-Agent Code Generation and Problem Solving through Simulation-Driven Planning and Debuggingcited by 31
  3. 2024MR-Ben: A Meta-Reasoning Benchmark for Evaluating System-2 Thinking in LLMscited by 30
  4. 2024Meta Reasoning for Large Language Modelscited by 29
  5. 2024AutoPSV: Automated Process-Supervised Verifiercited by 28
  6. 2024SPRIG: Improving Large Language Model Performance by System Prompt Optimizationcited by 28
  7. 2024Improving Physics Reasoning in Large Language Models Using Mixture of Refinement Agentscited by 22
  8. 2025Chain-of-Thought Prompting Obscures Hallucination Cues in Large Language Models: An Empirical Evaluationcited by 20
  9. 2023Auto-ICL: In-Context Learning without Human Supervisioncited by 18
  10. 2024Quantifying the Capabilities of LLMs across Scale and Precisioncited by 17
  11. 2024Learning From Correctness Without Prompting Makes LLM Efficient Reasonercited by 15
  12. 2025When Thinking Drifts: Evidential Grounding for Robust Video Reasoningcited by 15
  13. 2026Learning Global Hypothesis Space for Enhancing Synergistic Reasoning Chaincited by 15
  14. 2025Large Language Models are Autonomous Cyber Defenderscited by 14
  15. 2024Limits of Transformer Language Models on Learning to Compose Algorithmscited by 13
  16. 2024AnaloBench: Benchmarking the Identification of Abstract and Long-context Analogiescited by 13
  17. 2025Compositional Translation: A Novel LLM-based Approach for Low-resource Machine Translationcited by 13
  18. 2024Large Language Models are Contrastive Reasonerscited by 11
  19. 2024AMPO: Automatic Multi-Branched Prompt Optimizationcited by 11
  20. 2025Execution Guided Line-by-Line Code Generationcited by 10
  21. 2025Positional Biases Shift as Inputs Approach Context Window Limitscited by 9
  22. 2024Relevant or Random: Can LLMs Truly Perform Analogical Reasoning?cited by 8
  23. 2024Chain of Evidences and Evidence to Generate: Prompting for Context Grounded and Retrieval Augmented Reasoningcited by 7
  24. 2024When Reasoning Meets Information Aggregation: A Case Study with Sports Narrativescited by 7
  25. 2024Solving for X and Beyond: Can Large Language Models Solve Complex Math Problems with More-Than-Two Unknowns?cited by 7
  26. 2024Creativity in AI: Progresses and Challengescited by 7
  27. 2025Reliable Proof Generation with LLMs via Analogical Retrieval and Symbolic Verification: A Case Study in Euclidean Geometrycited by 7
  28. 2025Eliciting Reasoning in Language Models with Cognitive Toolscited by 6
  29. 2025E2Edev: Benchmarking Large Language Models in End-to-End Software Development Taskcited by 6
  30. 2026Unlocking LLM Creativity in Science through Analogical Reasoningcited by 6
  31. 2024DCR: Divide-and-Conquer Reasoning for Multi-choice Question Answering with LLMscited by 5
  32. 2024Evaluating LLMs with Multiple Problems at oncecited by 5
  33. 2026Counterfactual Graph for Multi-Agent LLM Calibrationcited by 5
  34. 2023Large Language Models are In-context Teachers for Knowledge Reasoningcited by 4
  35. 2024Self-Demos: Eliciting Out-of-Demonstration Generalizability in Large Language Modelscited by 4
  36. 2024Let's Be Self-generated via Step by Step: A Curriculum Learning Approach to Automated Reasoning with Large Language Modelscited by 4
  37. 2025From Token to Line: Enhancing Code Generation with a Long-Term Perspectivecited by 4
  38. 2025StyleBench: Evaluating thinking styles in Large Language Modelscited by 4

50 most cited of 107 All 107 (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. 2022Towards Understanding Chain-of-Thought Prompting: An Empirical Study of What Matters
  3. 2024Inductive Linguistic Reasoning with Large Language Models
  4. 2023Synthetic Prompting: Generating Chain-of-Thought Demonstrations for Large Language Models
  5. 2024Unveiling the Statistical Foundations of Chain-of-Thought Prompting Methods
  6. 2024ChainLM: Empowering Large Language Models with Improved Chain-of-Thought Prompting
  7. 2022Complexity-Based Prompting for Multi-Step Reasoning
  8. 2024Think Beyond Size: Adaptive Prompting for More Effective Reasoning