# Analogy Generation by Prompting Large Language Models: A Case Study of InstructGPT

arXiv: https://arxiv.org/abs/2210.04186 · HTML: https://mlsanity.com/paper/2210.04186/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 43 references that are in the map.
- First posted on arXiv 9 Oct 2022.

## Builds on (most cited first, 18 of 18)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing](https://mlsanity.com/paper/2107.13586/) (2021)
- [Calibrate Before Use: Improving Few-Shot Performance of Language Models](https://mlsanity.com/paper/2102.09690/) (2021)
- [BLEURT: Learning Robust Metrics for Text Generation](https://mlsanity.com/paper/2004.04696/) (2020)
- [Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity](https://mlsanity.com/paper/2104.08786/) (2021)
- [Ethical and social risks of harm from Language Models](https://mlsanity.com/paper/2112.04359/) (2021)
- [Hurdles to Progress in Long-form Question Answering](https://mlsanity.com/paper/2103.06332/) (2021)
- [Combating Adversarial Misspellings with Robust Word Recognition](https://mlsanity.com/paper/1905.11268/) (2019)
- [Abstraction and Analogy-Making in Artificial Intelligence](https://mlsanity.com/paper/2102.10717/) (2021)
- [Pretrained Language Models for Text Generation: A Survey](https://mlsanity.com/paper/2105.10311/) (2021)
- [CharBERT: Character-aware Pre-trained Language Model](https://mlsanity.com/paper/2011.01513/) (2020)
- [BERT is to NLP what AlexNet is to CV: Can Pre-Trained Language Models Identify Analogies?](https://mlsanity.com/paper/2105.04949/) (2021)
- [NeuSpell: A Neural Spelling Correction Toolkit](https://mlsanity.com/paper/2010.11085/) (2020)
- [Robsut Wrod Reocginiton via semi-Character Recurrent Neural Network](https://mlsanity.com/paper/1608.02214/) (2016)

## Built on by (most cited first, 27 of 27)

- [Language Model Behavior: A Comprehensive Survey](https://mlsanity.com/paper/2303.11504/) (2023)
- [Buffer of Thoughts: Thought-Augmented Reasoning with Large Language Models](https://mlsanity.com/paper/2406.04271/) (2024)
- [ChatGPT is not all you need. A State of the Art Review of large Generative AI models](https://mlsanity.com/paper/2301.04655/) (2023)
- [Determinants of LLM-assisted Decision-Making](https://mlsanity.com/paper/2402.17385/) (2024)
- [Thought Propagation: An Analogical Approach to Complex Reasoning with Large Language Models](https://mlsanity.com/paper/2310.03965/) (2023)
- [StoryAnalogy: Deriving Story-level Analogies from Large Language Models to Unlock Analogical Understanding](https://mlsanity.com/paper/2310.12874/) (2023)
- [Fluid Transformers and Creative Analogies: Exploring Large Language Models' Capacity for Augmenting Cross-Domain Analogical Creativity](https://mlsanity.com/paper/2302.12832/) (2023)
- [ANALOGYKB: Unlocking Analogical Reasoning of Language Models with A Million-scale Knowledge Base](https://mlsanity.com/paper/2305.05994/) (2023)
- [AnaloBench: Benchmarking the Identification of Abstract and Long-context Analogies](https://mlsanity.com/paper/2402.12370/) (2024)
- [Evaluating the Deductive Competence of Large Language Models](https://mlsanity.com/paper/2309.05452/) (2023)
- [Beneath Surface Similarity: Large Language Models Make Reasonable Scientific Analogies after Structure Abduction](https://mlsanity.com/paper/2305.12660/) (2023)
- [ParallelPARC: A Scalable Pipeline for Generating Natural-Language Analogies](https://mlsanity.com/paper/2403.01139/) (2024)
- [Can LLMs Correct Physicians, Yet? Investigating Effective Interaction Methods in the Medical Domain](https://mlsanity.com/paper/2403.20288/) (2024)
- [Mapping the Design Space of Interactions in Human-AI Text Co-creation Tasks](https://mlsanity.com/paper/2303.06430/) (2023)
- [Opportunities for Large Language Models and Discourse in Engineering Design](https://mlsanity.com/paper/2306.09169/) (2023)
- [Schema for In-Context Learning](https://mlsanity.com/paper/2510.13905/) (2025)
- [Elucidating STEM Concepts through Generative AI: A Multi-modal Exploration of Analogical Reasoning](https://mlsanity.com/paper/2308.10454/) (2023)
- [Boosting Scientific Concepts Understanding: Can Analogy from Teacher Models Empower Student Models?](https://mlsanity.com/paper/2406.11375/) (2024)
- [Large Vision-Language Models for Knowledge-Grounded Data Annotation of Memes](https://mlsanity.com/paper/2501.13851/) (2025)
- [RelBERT: Embedding Relations with Language Models](https://mlsanity.com/paper/2310.00299/) (2023)
- [Pairing Analogy-Augmented Generation with Procedural Memory for Procedural Q&A](https://mlsanity.com/paper/2409.01344/) (2024)
- [Past Meets Present: Creating Historical Analogy with Large Language Models](https://mlsanity.com/paper/2409.14820/) (2024)
- [Multilingual LLMs Are Not Multilingual Thinkers: Evidence from Hindi Analogy Evaluation](https://mlsanity.com/paper/2507.13238/) (2025)
- [ANVIL: Analogies and Videos for Lecturers](https://mlsanity.com/paper/2605.16295/) (2026)
- [Text Fact Transfer](https://mlsanity.com/paper/2310.14486/) (2023)
- [Large Language Models as a Tool for Mining Object Knowledge](https://mlsanity.com/paper/2410.12959/) (2024)
- [Structural Ranking of the Cognitive Plausibility of Computational Models of Analogy and Metaphors with the Minimal Cognitive Grid](https://mlsanity.com/paper/2605.01359/) (2026)

## Abstract (arXiv)

We propose a novel application of prompting Pre-trained Language Models (PLMs) to generate analogies and study how to design effective prompts for two task settings: generating a source concept analogous to a given target concept (aka Analogous Concept Generation or ACG), and generating an explanation of the similarity between a given pair of target concept and source concept (aka Analogous Explanation Generation or AEG). We found that it is feasible to prompt InstructGPT to generate meaningful analogies and the best prompts tend to be precise imperative statements especially with a low temperature setting. We also systematically analyzed the sensitivity of the InstructGPT model to prompt design, temperature, and injected spelling errors, and found that the model is particularly sensitive to certain variations (e.g., questions vs. imperative statements). Further, we conducted human evaluation on 1.4k of the generated analogies and found that the quality of generations varies substantially by model size. The largest InstructGPT model can achieve human-level performance at generating meaningful analogies for a given target while there is still room for improvement on the AEG task.