mlsanityData to 7 Oct 2026

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

arXiv 2210.04186 ↗First posted 9 Oct 2022cs.CL cs.AIcited by 27

Not on the map. Why?

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.

Key facts. Cited by 27 papers in the map (data through 7 Oct 2026). Builds on 18 of its 43 references that are in the map. First posted on arXiv 9 Oct 2022.

Builds on

18 of 43 references.

References · 18

  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. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,346
  6. 2021Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processingcited by 2,222
  7. 2021Calibrate Before Use: Improving Few-Shot Performance of Language Modelscited by 1,371
  8. 2020BLEURT: Learning Robust Metrics for Text Generationcited by 1,196
  9. 2021Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivitycited by 1,122
  10. 2021Ethical and social risks of harm from Language Modelscited by 957
  11. 2021Hurdles to Progress in Long-form Question Answeringcited by 166
  12. 2019Combating Adversarial Misspellings with Robust Word Recognitioncited by 162
6 more
  1. 2021Abstraction and Analogy-Making in Artificial Intelligencecited by 103
  2. 2021Pretrained Language Models for Text Generation: A Surveycited by 95
  3. 2020CharBERT: Character-aware Pre-trained Language Modelcited by 63
  4. 2021BERT is to NLP what AlexNet is to CV: Can Pre-Trained Language Models Identify Analogies?cited by 56
  5. 2020NeuSpell: A Neural Spelling Correction Toolkitcited by 31
  6. 2016Robsut Wrod Reocginiton via semi-Character Recurrent Neural Networkcited by 18

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 13; 2024: 9; 2025: 3; 2026: 2.

27 papers.

Sort:

By area:

  1. 2023Language Model Behavior: A Comprehensive Surveycited by 92
  2. 2024Buffer of Thoughts: Thought-Augmented Reasoning with Large Language Modelscited by 91
  3. 2023ChatGPT is not all you need. A State of the Art Review of large Generative AI modelscited by 85
  4. 2024Determinants of LLM-assisted Decision-Makingcited by 55
  5. 2023Thought Propagation: An Analogical Approach to Complex Reasoning with Large Language Modelscited by 37
  6. 2023StoryAnalogy: Deriving Story-level Analogies from Large Language Models to Unlock Analogical Understandingcited by 26
  7. 2023Fluid Transformers and Creative Analogies: Exploring Large Language Models' Capacity for Augmenting Cross-Domain Analogical Creativitycited by 23
  8. 2023ANALOGYKB: Unlocking Analogical Reasoning of Language Models with A Million-scale Knowledge Basecited by 16
  9. 2024AnaloBench: Benchmarking the Identification of Abstract and Long-context Analogiescited by 13
  10. 2023Evaluating the Deductive Competence of Large Language Modelscited by 12
  11. 2023Beneath Surface Similarity: Large Language Models Make Reasonable Scientific Analogies after Structure Abductioncited by 11
  12. 2024ParallelPARC: A Scalable Pipeline for Generating Natural-Language Analogiescited by 8
15 more
  1. 2024Can LLMs Correct Physicians, Yet? Investigating Effective Interaction Methods in the Medical Domaincited by 7
  2. 2023Mapping the Design Space of Interactions in Human-AI Text Co-creation Taskscited by 6
  3. 2023Opportunities for Large Language Models and Discourse in Engineering Designcited by 6
  4. 2025Schema for In-Context Learningcited by 4
  5. 2023Elucidating STEM Concepts through Generative AI: A Multi-modal Exploration of Analogical Reasoningcited by 3
  6. 2024Boosting Scientific Concepts Understanding: Can Analogy from Teacher Models Empower Student Models?cited by 3
  7. 2025Large Vision-Language Models for Knowledge-Grounded Data Annotation of Memescited by 2
  8. 2023RelBERT: Embedding Relations with Language Modelscited by 1
  9. 2024Pairing Analogy-Augmented Generation with Procedural Memory for Procedural Q&Acited by 1
  10. 2024Past Meets Present: Creating Historical Analogy with Large Language Modelscited by 1
  11. 2025Multilingual LLMs Are Not Multilingual Thinkers: Evidence from Hindi Analogy Evaluationcited by 1
  12. 2026ANVIL: Analogies and Videos for Lecturerscited by 1
  13. 2023Text Fact Transfercited by 0
  14. 2024Large Language Models as a Tool for Mining Object Knowledgecited by 0
  15. 2026Structural Ranking of the Cognitive Plausibility of Computational Models of Analogy and Metaphors with the Minimal Cognitive Gridcited by 0