---
title: "Least-to-most prompting enables complex reasoning in — 2022"
description: "Chain-of-thought prompting works well when test problems look like the worked examples in the prompt."
year: 2022
venue: "arXiv (Cornell University)"
source: "https://arxiv.org/abs/2205.10625"
arxiv: "2205.10625"
licence: "arXiv — non-exclusive licence to distribute"
licence_url: "http://arxiv.org/licenses/nonexclusive-distrib/1.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/al-2022-least-most-prompting-enables-complex/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/al-2022-least-most-prompting-enables-complex/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2022](https://md.research.elamur.ai/free/en/papers/2022/) / Least-to-most prompting enables complex reasoning in large language models

# Least-to-most prompting enables complex reasoning in large language models

**Year:** 2022 · **Venue:** arXiv (Cornell University) · **Licence:** [arXiv — non-exclusive licence to distribute](http://arxiv.org/licenses/nonexclusive-distrib/1.0/)

**Links:** [Publisher's page](https://arxiv.org/abs/2205.10625) · [PDF](https://arxiv.org/pdf/2205.10625) · [arXiv 2205.10625](https://arxiv.org/abs/2205.10625) · [OpenAlex](https://openalex.org/W4281483047)

**Citations:** 313 citations (openalex-snapshot · 2026-10-14) · [830](#cited-by) in our library, of the 140884 papers whose bibliographies we read

## Summary
Chain-of-thought prompting works well when test problems look like the worked examples in the prompt. It struggles when test problems are harder than those examples, for instance longer inputs or new combinations of known parts (easy-to-hard generalization). Zhou et al. from Google Research propose least-to-most prompting to fix this. It runs in two few-shot stages and needs no training or finetuning. First, the model splits a hard question into a sequence of simpler subquestions. Then it answers them in order, and each prompt includes the answers already produced. The authors test the method with GPT-3 code-davinci-002 on three task types: symbolic manipulation (last-letter concatenation), compositional generalization (SCAN), and math word problems (GSM8K, DROP). Least-to-most prompting handles problems much harder than its examples. On SCAN it scores at least 99% on every split, including the length split, using only 14 exemplars. This matters because it shows that good prompt design alone can give strong generalization to harder inputs. Specialized models that solve SCAN need over 15,000 training examples.

## Key points
- **Method:** a decomposition prompt produces the subproblems, then a solving prompt answers them one at a time. Each step adds the previous subquestion–answer pairs to the prompt, so the examples teach a base case plus a recursive step. The method can be combined with chain-of-thought or self-consistency, and for some tasks both stages fit in a single pass.
- **Last-letter concatenation:** test lists were built from Wiktionary words, with 500 lists for each length from 4 to 12. At length 12, least-to-most scores 74.0%, chain-of-thought 31.8% (up to 38.4% with 8 independent exemplars), and standard prompting 0%.
- **SCAN:** with least-to-most, code-davinci-002 reaches at least 99% accuracy on all splits, versus about 16% for chain-of-thought on the length split.
- **Math reasoning (GSM8K, DROP):** the gains are smaller on GSM8K overall (about 62% vs 61%) but larger on problems that need many solution steps. On DROP the improvement is clearer.
- The name comes from educational psychology, where it means helping a learner with a sequence of prompts that grows step by step. The paper's appendix includes all the prompts.

**Note:** the paper text you sent had its middle section cut out. The SCAN figure of at least 99% on every split comes from the abstract you provided. The other numbers in the Math reasoning point (GSM8K, DROP) and the about-16% SCAN figure for chain-of-thought come from my own knowledge of the paper, not from your excerpt, so please check them against the full PDF before adding this to the library.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

Fields: [Mathematics & statistics](https://md.research.elamur.ai/free/en/shelves/mathematics/)

Topics: [Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/) · [Reasoning](https://md.research.elamur.ai/free/en/topics/reasoning/)

## Cited by

Cited by

830 papers of our library cite it (of the 140884 whose bibliographies we read); 68 of them have a page here, 762 not yet.

- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://md.research.elamur.ai/free/en/papers/deepseek-2025-ai-deepseek-r1-incentivizing-reasoning-capability/)
- [A Survey of Large Language Models](https://md.research.elamur.ai/free/en/papers/zhao-2023-survey-large-language-models/)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://md.research.elamur.ai/free/en/papers/yao-2022-react-synergizing-reasoning-acting-language/)
- [Emergent Abilities of Large Language Models](https://md.research.elamur.ai/free/en/papers/wei-2022-emergent-abilities-large-language-models/)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://md.research.elamur.ai/free/en/papers/gao-2023-retrieval-augmented-generation-large-language/)
- [Qwen Technical Report](https://md.research.elamur.ai/free/en/papers/bai-2023-qwen-technical-report/)
- [The Rise and Potential of Large Language Model Based Agents: A Survey](https://md.research.elamur.ai/free/en/papers/xi-2023-rise-potential-large-language/)
- [Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them](https://md.research.elamur.ai/free/en/papers/suzgun-2023-challenging-big-bench-tasks-whether/)
- [A Survey on In-context Learning](https://md.research.elamur.ai/free/en/papers/dong-2023-survey-context-learning/)
- [A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT](https://md.research.elamur.ai/free/en/papers/white-2023-prompt-pattern-catalog-enhance-prompt/)
- [Is ChatGPT a General-Purpose Natural Language Processing Task Solver?](https://md.research.elamur.ai/free/en/papers/qin-2023-chatgpt-general-purpose-natural-language/)
- [Towards Reasoning in Large Language Models: A Survey](https://md.research.elamur.ai/free/en/papers/huang-2023-reasoning-large-language-models-survey/)
- [CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society](https://md.research.elamur.ai/free/en/papers/li-2023-camel-communicative-agents-mind/)
- [Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting](https://md.research.elamur.ai/free/en/papers/turpin-2023-language-models-don-t-always/)
- [Large Language Models Can Self-Improve](https://md.research.elamur.ai/free/en/papers/huang-2023-large-language-models-can-self/)
- [MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models](https://md.research.elamur.ai/free/en/papers/yu-2023-metamath-bootstrap-your-own-mathematical/)
- [Large Language Models Can Be Easily Distracted by Irrelevant Context](https://md.research.elamur.ai/free/en/papers/shi-2023-large-language-models-easily-distracted/)
- [C-Eval: A Multi-Level Multi-Discipline Chinese Evaluation Suite for Foundation Models](https://md.research.elamur.ai/free/en/papers/huang-2023-c-eval-multi-level-multi/)
- [DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correction](https://md.research.elamur.ai/free/en/papers/pourreza-2023-din-sql-decomposed-context-learning/)
- [Large Language Models Cannot Self-Correct Reasoning Yet](https://md.research.elamur.ai/free/en/papers/huang-2023-large-language-models-cannot-self/)
- [Large Language Models as Optimizers](https://md.research.elamur.ai/free/en/papers/yang-2023-large-language-models-optimizers/)
- [Logic-LM: Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoning](https://md.research.elamur.ai/free/en/papers/pan-2023-logic-lm-empowering-large-language/)
- [A Survey on Large Language Models for Code Generation](https://md.research.elamur.ai/free/en/papers/jiang-2024-survey-large-language-models-code/)
- [WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct](https://md.research.elamur.ai/free/en/papers/luo-2023-wizardmath-empowering-mathematical-reasoning-large/)
- [Augmented Language Models: a Survey](https://md.research.elamur.ai/free/en/papers/mialon-2023-augmented-language-models-survey/)
- [Faithful Chain-of-Thought Reasoning](https://md.research.elamur.ai/free/en/papers/lyu-2023-faithful-chain-thought-reasoning/)
- [Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models](https://md.research.elamur.ai/free/en/papers/wu-2023-visual-chatgpt-talking-drawing-editing/)
- [Large Language Models are Better Reasoners with Self-Verification](https://md.research.elamur.ai/free/en/papers/weng-2023-large-language-models-are-better/)
- [Challenges and Applications of Large Language Models](https://md.research.elamur.ai/free/en/papers/kaddour-2023-challenges-applications-large-language-models/)
- [Multi-step Jailbreaking Privacy Attacks on ChatGPT](https://md.research.elamur.ai/free/en/papers/li-2023-multi-step-jailbreaking-privacy-attacks/)
- [Multimodal Chain-of-Thought Reasoning in Language Models](https://md.research.elamur.ai/free/en/papers/zhang-2023-multimodal-chain-thought-reasoning-language/)
- [Prompting Large Language Model for Machine Translation: A Case Study](https://md.research.elamur.ai/free/en/papers/zhang-2023-prompting-large-language-model-machine/)
- [MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuning](https://md.research.elamur.ai/free/en/papers/yue-2023-mammoth-building-math-generalist-models/)
- [Larger language models do in-context learning differently](https://md.research.elamur.ai/free/en/papers/wei-2023-larger-language-models-context-learning/)
- [Measuring Faithfulness in Chain-of-Thought Reasoning](https://md.research.elamur.ai/free/en/papers/lanham-2023-measuring-faithfulness-chain-thought-reasoning/)
- [Language Models can Solve Computer Tasks](https://md.research.elamur.ai/free/en/papers/kim-2023-language-models-solve-computer-tasks/)
- [FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance](https://md.research.elamur.ai/free/en/papers/chen-2023-frugalgpt-use-large-language-models/)
- [ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving](https://md.research.elamur.ai/free/en/papers/gou-2023-tora-tool-integrated-reasoning-agent/)
- [Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment](https://md.research.elamur.ai/free/en/papers/liu-2023-trustworthy-llms-survey-guideline-evaluating/)
- [Making Language Models Better Reasoners with Step-Aware Verifier](https://md.research.elamur.ai/free/en/papers/li-2023-making-language-models-better-reasoners/)
- [Distilling Reasoning Capabilities into Smaller Language Models](https://md.research.elamur.ai/free/en/papers/shridhar-2023-distilling-reasoning-capabilities-into-smaller/)
- [ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search](https://md.research.elamur.ai/free/en/papers/zhang-2024-rest-mcts-llm-self-training/)
- [The Prompt Report: A Systematic Survey of Prompt Engineering Techniques](https://md.research.elamur.ai/free/en/papers/schulhoff-2024-prompt-report-systematic-survey-prompt/)
- [Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researchers](https://md.research.elamur.ai/free/en/papers/si-2024-llms-generate-novel-research/)
- [Large Language Models are few(1)-shot Table Reasoners](https://md.research.elamur.ai/free/en/papers/chen-2023-large-language-models-are-few/)
- [On Second Thought, Let's Not Think Step by Step! Bias and Toxicity in Zero-Shot Reasoning](https://md.research.elamur.ai/free/en/papers/shaikh-2023-second-thought-let-s-not/)
- [Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models](https://md.research.elamur.ai/free/en/papers/chen-2025-towards-reasoning-era-survey-long/)
- [LINC: A Neurosymbolic Approach for Logical Reasoning by Combining Language Models with First-Order Logic Provers](https://md.research.elamur.ai/free/en/papers/olausson-2023-linc-neurosymbolic-approach-logical-reasoning/)
- [Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution](https://md.research.elamur.ai/free/en/papers/fernando-2023-promptbreeder-self-referential-self-improvement/)
- [Reasoning with Language Model Prompting: A Survey](https://md.research.elamur.ai/free/en/papers/qiao-2022-reasoning-language-model-prompting-survey/)
- [TheoremQA: A Theorem-driven Question Answering Dataset](https://md.research.elamur.ai/free/en/papers/chen-2023-theoremqa-theorem-driven-question-answering/)
- [Can GPT-3 Perform Statutory Reasoning?](https://md.research.elamur.ai/free/en/papers/blair-2023-stanek-gpt-3-perform-statutory-reasoning/)
- [SciBench: Evaluating College-Level Scientific Problem-Solving Abilities of Large Language Models](https://md.research.elamur.ai/free/en/papers/wang-2023-scibench-evaluating-college-level-scientific/)
- [Self-Evaluation Guided Beam Search for Reasoning](https://md.research.elamur.ai/free/en/papers/xie-2023-self-evaluation-guided-beam-search/)
- [Verify-and-Edit: A Knowledge-Enhanced Chain-of-Thought Framework](https://md.research.elamur.ai/free/en/papers/zhao-2023-verify-edit-knowledge-enhanced-chain/)
- [A Stitch in Time Saves Nine: Detecting and Mitigating Hallucinations of LLMs by Validating Low-Confidence Generation](https://md.research.elamur.ai/free/en/papers/varshney-2023-stitch-time-saves-nine-detecting/)
- [Token-Budget-Aware LLM Reasoning](https://md.research.elamur.ai/free/en/papers/han-2024-token-budget-aware-llm-reasoning/)
- [To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning](https://md.research.elamur.ai/free/en/papers/sprague-2024-cot-cot-chain-thought-helps/)
- [ReFT: Reasoning with Reinforced Fine-Tuning](https://md.research.elamur.ai/free/en/papers/trung-2024-reft-reasoning-reinforced-fine-tuning/)
- [Deductive Verification of Chain-of-Thought Reasoning](https://md.research.elamur.ai/free/en/papers/ling-2023-deductive-verification-chain-thought-reasoning/)
- [Cross-lingual Prompting: Improving Zero-shot Chain-of-Thought Reasoning across Languages](https://md.research.elamur.ai/free/en/papers/qin-2023-cross-lingual-prompting-improving-zero/)
- [Solving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-Verification](https://md.research.elamur.ai/free/en/papers/zhou-2023-solving-challenging-math-word-problems/)
- [GSM-Plus: A Comprehensive Benchmark for Evaluating the Robustness of LLMs as Mathematical Problem Solvers](https://md.research.elamur.ai/free/en/papers/li-2024-gsm-plus-comprehensive-benchmark-evaluating/)
- [TokenSkip: Controllable Chain-of-Thought Compression in LLMs](https://md.research.elamur.ai/free/en/papers/xia-2025-tokenskip-controllable-chain-thought-compression/)
- [How Is LLM Reasoning Distracted by Irrelevant Context? An Analysis Using a Controlled Benchmark](https://md.research.elamur.ai/free/en/papers/yang-2025-llm-reasoning-distracted-irrelevant-context/)
- [Let's Simplify Step by Step: Guiding LLM Towards Multilingual Unsupervised Proficiency-Controlled Sentence Simplification](https://md.research.elamur.ai/free/en/papers/zhang-2026-let-s-simplify-step-step/)
- [KCIF: Knowledge-Conditioned Instruction Following](https://md.research.elamur.ai/free/en/papers/murthy-2026-kcif-knowledge-conditioned-instruction-following/)
- [Questionnaire Meets LLM: A Benchmark and Empirical Study of Structural Skills for Understanding Questions and Responses](https://md.research.elamur.ai/free/en/papers/nguyen-2026-questionnaire-meets-llm-benchmark-empirical/)

## Cite

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@misc{anon2022least,
  title = {{Least-to-most prompting enables complex reasoning in large language models}},
  year = {2022},
  eprint = {2205.10625},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2205.10625}
}
```

- [← previous Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity](https://md.research.elamur.ai/free/en/papers/lu-2022-fantastically-ordered-prompts-where-find/)
- [next → MTEB: Massive Text Embedding Benchmark](https://md.research.elamur.ai/free/en/papers/muennighoff-2022-mteb-massive-text-embedding-benchmark/)
- [↑ back to papers of 2022](https://md.research.elamur.ai/free/en/papers/2022/)

## References

29 references, 6 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Ekin Akyürek, Afra Feyza Akyürek, and Jacob Andreas. Learning to recombine and resample data for compositional generalization. In International Conference on Learning Representations, 2021. [find](https://scholar.google.com/scholar?q=Ekin+Akyu%CC%88rek%2C+Afra+Feyza+Akyu%CC%88rek%2C+and+Jacob+Andreas%2E+Learning+to+recombine+and+resample+data+for+compositional+generalization%2E+In+International+Conference+on+Learning+Representations%2C+2021%2E)
2. Jacob Andreas. Good-enough compositional data augmentation. In Annual Meeting of the Association for Computational Linguistics, 2020. [find](https://scholar.google.com/scholar?q=Jacob+Andreas%2E+Good%2Denough+compositional+data+augmentation%2E+In+Annual+Meeting+of+the+Association+for+Computational+Linguistics%2C+2020%2E) [our card](https://md.research.elamur.ai/free/en/papers/andreas-2020-good-enough-compositional-data-augmentation/)
3. Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et al. Language models are few-shot learners. Advances in neural information processing systems, 33:1877–1901, 2020. [find](https://scholar.google.com/scholar?q=Tom+Brown%2C+Benjamin+Mann%2C+Nick+Ryder%2C+Melanie+Subbiah%2C+Jared+D+Kaplan%2C+Prafulla+Dhariwal%2C+Arvind+Neelakantan%2C+Pranav+Shyam%2C+Girish+Sastry%2C+Amanda+Askell%2C+et+al%2E+Language+models+are+few%2Dshot+learners%2E+)
4. Xinyun Chen, Chen Liang, Adams Wei Yu, Dawn Song, and Denny Zhou. Compositional generalization via neural-symbolic stack machines. Advances in Neural Information Processing Systems, 33:1690–1701, 2020. [find](https://scholar.google.com/scholar?q=Xinyun+Chen%2C+Chen+Liang%2C+Adams+Wei+Yu%2C+Dawn+Song%2C+and+Denny+Zhou%2E+Compositional+generalization+via+neural%2Dsymbolic+stack+machines%2E+Advances+in+Neural+Information+Processing+Systems%2C+33%3A1690%E2%80%931701%2C+2020)
5. Aakanksha Chowdhery, Sharan Narang, Jacob Devlin, Maarten Bosma, Gaurav Mishra, Adam Roberts, Paul Barham, Hyung Won Chung, Charles Sutton, Sebastian Gehrmann, et al. PaLM: Scaling language modeling with pathways. arXiv preprint arXiv:2204.02311, 2022. [find](https://scholar.google.com/scholar?q=Aakanksha+Chowdhery%2C+Sharan+Narang%2C+Jacob+Devlin%2C+Maarten+Bosma%2C+Gaurav+Mishra%2C+Adam+Roberts%2C+Paul+Barham%2C+Hyung+Won+Chung%2C+Charles+Sutton%2C+Sebastian+Gehrmann%2C+et+al%2E+PaLM%3A+Scaling+language+modeling+w)
6. Karl Cobbe, Vineet Kosaraju, Mohammad Bavarian, Jacob Hilton, Reiichiro Nakano, Christopher Hesse, and John Schulman. Training verifiers to solve math word problems. arXiv preprint arXiv:2110.14168, 2021. [find](https://scholar.google.com/scholar?q=Karl+Cobbe%2C+Vineet+Kosaraju%2C+Mohammad+Bavarian%2C+Jacob+Hilton%2C+Reiichiro+Nakano%2C+Christopher+Hesse%2C+and+John+Schulman%2E+Training+verifiers+to+solve+math+word+problems%2E+arXiv+preprint+arXiv%3A2110%2E14168%2C+2) [our card](https://md.research.elamur.ai/free/en/papers/cobbe-2021-training-verifiers-solve-math-word/)
7. Honghua Dong, Jiayuan Mao, Tian Lin, Chong Wang, Lihong Li, and Denny Zhou. Neural logic machines. In International Conference on Learning Representations, 2019. [find](https://scholar.google.com/scholar?q=Honghua+Dong%2C+Jiayuan+Mao%2C+Tian+Lin%2C+Chong+Wang%2C+Lihong+Li%2C+and+Denny+Zhou%2E+Neural+logic+machines%2E+In+International+Conference+on+Learning+Representations%2C+2019%2E)
8. Dheeru Dua, Yizhong Wang, Pradeep Dasigi, Gabriel Stanovsky, Sameer Singh, and Matt Gardner. DROP: A reading comprehension benchmark requiring discrete reasoning over paragraphs. arXiv preprint arXiv:1903.00161, 2019. [find](https://scholar.google.com/scholar?q=Dheeru+Dua%2C+Yizhong+Wang%2C+Pradeep+Dasigi%2C+Gabriel+Stanovsky%2C+Sameer+Singh%2C+and+Matt+Gardner%2E+DROP%3A+A+reading+comprehension+benchmark+requiring+discrete+reasoning+over+paragraphs%2E+arXiv+preprint+arXiv%3A) [our card](https://md.research.elamur.ai/free/en/papers/dua-2019-drop-reading-comprehension-benchmark-requiring/)
9. Mor Geva, Daniel Khashabi, Elad Segal, Tushar Khot, Dan Roth, and Jonathan Berant. Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies. Transactions of the Association for Computational Linguistics (TACL), 2021. [find](https://scholar.google.com/scholar?q=Mor+Geva%2C+Daniel+Khashabi%2C+Elad+Segal%2C+Tushar+Khot%2C+Dan+Roth%2C+and+Jonathan+Berant%2E+Did+Aristotle+Use+a+Laptop%3F+A+Question+Answering+Benchmark+with+Implicit+Reasoning+Strategies%2E+Transactions+of+the+As)
10. Jonathan Gordon, David Lopez-Paz, Marco Baroni, and Diane Bouchacourt. Permutation equivariant models for compositional generalization in language. In International Conference on Learning Representations, 2020. [find](https://scholar.google.com/scholar?q=Jonathan+Gordon%2C+David+Lopez%2DPaz%2C+Marco+Baroni%2C+and+Diane+Bouchacourt%2E+Permutation+equivariant+models+for+compositional+generalization+in+language%2E+In+International+Conference+on+Learning+Representati)
11. Jonathan Herzig and Jonathan Berant. Span-based semantic parsing for compositional generalization. In Annual Meeting of the Association for Computational Linguistics, 2021. [find](https://scholar.google.com/scholar?q=Jonathan+Herzig+and+Jonathan+Berant%2E+Span%2Dbased+semantic+parsing+for+compositional+generalization%2E+In+Annual+Meeting+of+the+Association+for+Computational+Linguistics%2C+2021%2E)
12. Daniel Keysers, Nathanael Schärli, Nathan Scales, Hylke Buisman, Daniel Furrer, Sergii Kashubin, Nikola Momchev, Danila Sinopalnikov, Lukasz Stafiniak, Tibor Tihon, et al. Measuring compositional generalization: A comprehensive method on realistic data. International Conference on Learning Represen… [find](https://scholar.google.com/scholar?q=Daniel+Keysers%2C+Nathanael+Scha%CC%88rli%2C+Nathan+Scales%2C+Hylke+Buisman%2C+Daniel+Furrer%2C+Sergii+Kashubin%2C+Nikola+Momchev%2C+Danila+Sinopalnikov%2C+Lukasz+Stafiniak%2C+Tibor+Tihon%2C+et+al%2E+Measuring+compositional+gen)
13. Yoon Kim. Sequence-to-sequence learning with latent neural grammars. Advances in Neural Information Processing Systems, 34, 2021. [find](https://scholar.google.com/scholar?q=Yoon+Kim%2E+Sequence%2Dto%2Dsequence+learning+with+latent+neural+grammars%2E+Advances+in+Neural+Information+Processing+Systems%2C+34%2C+2021%2E)
14. Brenden Lake and Marco Baroni. Generalization without systematicity: On the compositional skills of sequence-to-sequence recurrent networks. In International conference on machine learning, pp. 2873–2882. PMLR, 2018. [find](https://scholar.google.com/scholar?q=Brenden+Lake+and+Marco+Baroni%2E+Generalization+without+systematicity%3A+On+the+compositional+skills+of+sequence%2Dto%2Dsequence+recurrent+networks%2E+In+International+conference+on+machine+learning%2C+pp%2E+2873%E2%80%932)
15. Brenden M Lake. Compositional generalization through meta sequence-to-sequence learning. Advances in neural information processing systems, 32, 2019. [find](https://scholar.google.com/scholar?q=Brenden+M+Lake%2E+Compositional+generalization+through+meta+sequence%2Dto%2Dsequence+learning%2E+Advances+in+neural+information+processing+systems%2C+32%2C+2019%2E)
16. Yuanpeng Li, Liang Zhao, Jianyu Wang, and Joel Hestness. Compositional generalization for primitive substitutions. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pp. 4… [find](https://scholar.google.com/scholar?q=Yuanpeng+Li%2C+Liang+Zhao%2C+Jianyu+Wang%2C+and+Joel+Hestness%2E+Compositional+generalization+for+primitive+substitutions%2E+In+Proceedings+of+the+2019+Conference+on+Empirical+Methods+in+Natural+Language+Proces)
17. Myrna E Libby, Julie S Weiss, Stacie Bancroft, and William H Ahearn. A comparison of most-to-least and least-to-most prompting on the acquisition of solitary play skills. Behavior analysis in practice, 1(1):37–43, 2008. [find](https://scholar.google.com/scholar?q=Myrna+E+Libby%2C+Julie+S+Weiss%2C+Stacie+Bancroft%2C+and+William+H+Ahearn%2E+A+comparison+of+most%2Dto%2Dleast+and+least%2Dto%2Dmost+prompting+on+the+acquisition+of+solitary+play+skills%2E+Behavior+analysis+in+practice)
18. Wang Ling, Dani Yogatama, Chris Dyer, and Phil Blunsom. Program induction by rationale generation: Learning to solve and explain algebraic word problems. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2017. [find](https://scholar.google.com/scholar?q=Wang+Ling%2C+Dani+Yogatama%2C+Chris+Dyer%2C+and+Phil+Blunsom%2E+Program+induction+by+rationale+generation%3A+Learning+to+solve+and+explain+algebraic+word+problems%2E+In+Proceedings+of+the+55th+Annual+Meeting+of+t)
19. Qian Liu, Shengnan An, Jian-Guang Lou, Bei Chen, Zeqi Lin, Yan Gao, Bin Zhou, Nanning Zheng, and Dongmei Zhang. Compositional generalization by learning analytical expressions. Advances in Neural Information Processing Systems, 33:11416–11427, 2020. [find](https://scholar.google.com/scholar?q=Qian+Liu%2C+Shengnan+An%2C+Jian%2DGuang+Lou%2C+Bei+Chen%2C+Zeqi+Lin%2C+Yan+Gao%2C+Bin+Zhou%2C+Nanning+Zheng%2C+and+Dongmei+Zhang%2E+Compositional+generalization+by+learning+analytical+expressions%2E+Advances+in+Neural+Info)
20. Maxwell Nye, Armando Solar-Lezama, Josh Tenenbaum, and Brenden M Lake. Learning compositional rules via neural program synthesis. Advances in Neural Information Processing Systems, 33:10832–10842, 2020. [find](https://scholar.google.com/scholar?q=Maxwell+Nye%2C+Armando+Solar%2DLezama%2C+Josh+Tenenbaum%2C+and+Brenden+M+Lake%2E+Learning+compositional+rules+via+neural+program+synthesis%2E+Advances+in+Neural+Information+Processing+Systems%2C+33%3A10832%E2%80%9310842%2C+202)
21. Ethan Perez, Patrick Lewis, Wen-tau Yih, Kyunghyun Cho, and Douwe Kiela. Unsupervised question decomposition for question answering. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 8864–8880, 2020. [find](https://scholar.google.com/scholar?q=Ethan+Perez%2C+Patrick+Lewis%2C+Wen%2Dtau+Yih%2C+Kyunghyun+Cho%2C+and+Douwe+Kiela%2E+Unsupervised+question+decomposition+for+question+answering%2E+In+Proceedings+of+the+2020+Conference+on+Empirical+Methods+in+Natur) [our card](https://md.research.elamur.ai/free/en/papers/perez-2020-unsupervised-question-decomposition-question-answering/)
22. Jake Russin, Jason Jo, Randall C O’Reilly, and Yoshua Bengio. Compositional generalization in a deep seq2seq model by separating syntax and semantics. arXiv preprint arXiv:1904.09708, 2019. [find](https://scholar.google.com/scholar?q=Jake+Russin%2C+Jason+Jo%2C+Randall+C+O%E2%80%99Reilly%2C+and+Yoshua+Bengio%2E+Compositional+generalization+in+a+deep+seq2seq+model+by+separating+syntax+and+semantics%2E+arXiv+preprint+arXiv%3A1904%2E09708%2C+2019%2E)
23. Avi Schwarzschild, Eitan Borgnia, Arjun Gupta, Furong Huang, Uzi Vishkin, Micah Goldblum, and Tom Goldstein. Can you learn an algorithm? generalizing from easy to hard problems with recurrent networks. Advances in Neural Information Processing Systems, 34, 2021. [find](https://scholar.google.com/scholar?q=Avi+Schwarzschild%2C+Eitan+Borgnia%2C+Arjun+Gupta%2C+Furong+Huang%2C+Uzi+Vishkin%2C+Micah+Goldblum%2C+and+Tom+Goldstein%2E+Can+you+learn+an+algorithm%3F+generalizing+from+easy+to+hard+problems+with+recurrent+networks)
24. Peter Shaw, Ming-Wei Chang, Panupong Pasupat, and Kristina Toutanova. Compositional generalization and natural language variation: Can a semantic parsing approach handle both? In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint… [find](https://scholar.google.com/scholar?q=Peter+Shaw%2C+Ming%2DWei+Chang%2C+Panupong+Pasupat%2C+and+Kristina+Toutanova%2E+Compositional+generalization+and+natural+language+variation%3A+Can+a+semantic+parsing+approach+handle+both%3F+In+Proceedings+of+the+59)
25. Boshi Wang, Xiang Deng, and Huan Sun. Shepherd pre-trained language models to develop a train of thought: An iterative prompting approach. arXiv preprint arXiv:2203.08383, 2022a. [find](https://scholar.google.com/scholar?q=Boshi+Wang%2C+Xiang+Deng%2C+and+Huan+Sun%2E+Shepherd+pre%2Dtrained+language+models+to+develop+a+train+of+thought%3A+An+iterative+prompting+approach%2E+arXiv+preprint+arXiv%3A2203%2E08383%2C+2022a%2E)
26. Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc Le, Ed Chi, and Denny Zhou. Self-consistency improves chain of thought reasoning in language models. arXiv preprint arXiv:2203.11171, 2022b. [find](https://scholar.google.com/scholar?q=Xuezhi+Wang%2C+Jason+Wei%2C+Dale+Schuurmans%2C+Quoc+Le%2C+Ed+Chi%2C+and+Denny+Zhou%2E+Self%2Dconsistency+improves+chain+of+thought+reasoning+in+language+models%2E+arXiv+preprint+arXiv%3A2203%2E11171%2C+2022b%2E) [our card](https://md.research.elamur.ai/free/en/papers/wang-2022-self-consistency-improves-chain-thought/)
27. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Ed Chi, Brian Ichter, Fei Xia, Quoc Le, and Denny Zhou. Chain of thought prompting elicits reasoning in large language models. Advances in Neural Information Processing Systems, 35, 2022. [find](https://scholar.google.com/scholar?q=Jason+Wei%2C+Xuezhi+Wang%2C+Dale+Schuurmans%2C+Maarten+Bosma%2C+Ed+Chi%2C+Brian+Ichter%2C+Fei+Xia%2C+Quoc+Le%2C+and+Denny+Zhou%2E+Chain+of+thought+prompting+elicits+reasoning+in+large+language+models%2E+Advances+in+Neura) [our card](https://md.research.elamur.ai/free/en/papers/wei-2022-chain-thought-prompting-elicits-reasoning/)
28. Tongshuang Wu, Michael Terry, and Carrie Jun Cai. AI chains: Transparent and controllable human-AI interaction by chaining large language model prompts. In CHI Conference on Human Factors in Computing Systems, pp. 1–22, 2022. [find](https://scholar.google.com/scholar?q=Tongshuang+Wu%2C+Michael+Terry%2C+and+Carrie+Jun+Cai%2E+AI+chains%3A+Transparent+and+controllable+human%2DAI+interaction+by+chaining+large+language+model+prompts%2E+In+CHI+Conference+on+Human+Factors+in+Computing)
29. Jingfeng Yang, Haoming Jiang, Qingyu Yin, Danqing Zhang, Bing Yin, and Diyi Yang. Seqzero: Few-shot compositional semantic parsing with sequential prompts and zero-shot models. arXiv preprint arXiv:2205.07381, 2022. [find](https://scholar.google.com/scholar?q=Jingfeng+Yang%2C+Haoming+Jiang%2C+Qingyu+Yin%2C+Danqing+Zhang%2C+Bing+Yin%2C+and+Diyi+Yang%2E+Seqzero%3A+Few%2Dshot+compositional+semantic+parsing+with+sequential+prompts+and+zero%2Dshot+models%2E+arXiv+preprint+arXiv%3A22)