Prompting & Reasoning
In-context learning, chain-of-thought, few-shot prompting, eliciting reasoning in LMs.
A topic in the Science corpus, drawn from 330 papers.
Trusted voices in Prompting & Reasoning
Ordered by the trust Prompting & Reasoning's own network concentrates on each researcher, most first.
- Timo Schick — trusted by 216 researchers here
- Hinrich Schütze — trusted by 214 researchers here
- Brian Lester — trusted by 142 researchers here
- Quoc V. Le — trusted by 97 researchers here
- Rami Al-Rfou — trusted by 102 researchers here
- Noah Constant — trusted by 100 researchers here
- Jason Wei — trusted by 76 researchers here
- Bryan McCann — trusted by 65 researchers here
- Yejin Choi — trusted by 58 researchers here
- Richard Socher — trusted by 65 researchers here
- Danqi Chen — trusted by 58 researchers here
- Adam Fisch — trusted by 55 researchers here
Most-cited papers in Prompting & Reasoning
Ordered by the recorded citation count from the source corpus; a citation is not an endorsement.
- Language Models are Few-Shot Learners (2020, Neural Information Processing Systems) — 61,005 citations
- Chain of Thought Prompting Elicits Reasoning in Large Language Models (2022, Neural Information Processing Systems) — 20,310 citations
- Judging LLM-as-a-judge with MT-Bench and Chatbot Arena (2023) — 9,887 citations
- Training Verifiers to Solve Math Word Problems (2021) — 9,717 citations
- ReAct: Synergizing Reasoning and Acting in Language Models (2022, International Conference on Learning Representations) — 8,935 citations
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models (2024) — 7,648 citations
- Large Language Models are Zero-Shot Reasoners (2022) — 7,591 citations
- Self-Consistency Improves Chain of Thought Reasoning in Language Models (2022) — 7,218 citations
- The Power of Scale for Parameter-Efficient Prompt Tuning (2021) — 5,785 citations
- Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing (2021) — 5,562 citations
- DeepSeek-R1 incentivizes reasoning in LLMs through reinforcement learning (2025, Nature) — 5,477 citations
- Finetuned Language Models Are Zero-Shot Learners (2021) — 5,221 citations
- Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge (2018) — 5,112 citations
- HellaSwag: Can a Machine Really Finish Your Sentence? (2019) — 4,547 citations
- Tree of Thoughts: Deliberate Problem Solving with Large Language Models (2023) — 4,499 citations
- Lost in the Middle: How Language Models Use Long Contexts (2023) — 4,355 citations
- Learning to Prompt for Vision-Language Models (2021) — 4,174 citations
- Program Synthesis with Large Language Models (2021) — 4,124 citations
- Let's Verify Step by Step (2023) — 3,887 citations
- Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering (2022) — 2,503 citations
- Conditional Prompt Learning for Vision-Language Models (2022) — 2,313 citations
- Making Pre-trained Language Models Better Few-shot Learners (2021) — 2,303 citations
- Rethinking the Role of Demonstrations: What Makes In-Context Learning Work? (2022) — 2,090 citations
- Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them (2022) — 2,044 citations
- Multitask Prompted Training Enables Zero-Shot Task Generalization (2021) — 2,030 citations
- Reasoning (2019) — 2,027 citations
- Calibrate Before Use: Improving Few-Shot Performance of Language Models (2021) — 1,964 citations
- Exploiting Cloze-Questions for Few-Shot Text Classification and Natural Language Inference (2020) — 1,862 citations
- Least-to-Most Prompting Enables Complex Reasoning in Large Language Models (2022) — 1,834 citations
- What Makes Good In-Context Examples for GPT-3? (2021) — 1,798 citations
- Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity (2021) — 1,596 citations
- Large Language Models Are Human-Level Prompt Engineers (2022) — 1,479 citations
- CTRL: A Conditional Transformer Language Model for Controllable Generation (2019) — 1,445 citations
- Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks (2022) — 1,410 citations
- Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigm (2021) — 1,354 citations
- Learning to Prompt for Continual Learning (2021) — 1,330 citations
- Few-shot Learning with Retrieval Augmented Language Models (2022, Journal of machine learning research) — 1,295 citations
- WizardLM: Empowering Large Pre-Trained Language Models to Follow Complex Instructions (2023) — 1,266 citations
- Plug and Play Language Models: A Simple Approach to Controlled Text Generation (2019) — 1,229 citations
- Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions (2022) — 1,143 citations
- MaPLe: Multi-modal Prompt Learning (2022) — 1,127 citations
- P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks (2021) — 1,125 citations
- It’s Not Just Size That Matters: Small Language Models Are Also Few-Shot Learners (2020) — 1,122 citations
- P-Tuning: Prompt Tuning Can Be Comparable to Fine-tuning Across Scales and Tasks (2022) — 1,117 citations
- Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks (2022) — 1,112 citations
- An Explanation of In-context Learning as Implicit Bayesian Inference (2021) — 1,108 citations
- Show Your Work: Scratchpads for Intermediate Computation with Language Models (2021) — 1,075 citations
- Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations (2023) — 1,036 citations
- Program Induction by Rationale Generation: Learning to Solve and Explain Algebraic Word Problems (2017) — 1,014 citations
- Automatic Chain of Thought Prompting in Large Language Models (2022) — 1,007 citations
Most active researchers
By papers in this topic: a volume measure, not trust.
- Yejin Choi — 18 papers
- Hannaneh Hajishirzi — 13 papers
- Luke S. Zettlemoyer — 11 papers
- Peter Clark — 11 papers
- Quoc V. Le — 9 papers
- Jason Wei — 8 papers
- Sean Welleck — 8 papers
- Tushar Khot — 8 papers
- Yuhuai Wu — 8 papers
- Denny Zhou — 8 papers
- Noah A. Smith — 7 papers
- Jonathan Berant — 7 papers