mlsanityData to 7 Oct 2026

Fluid Transformers and Creative Analogies: Exploring Large Language Models' Capacity for Augmenting Cross-Domain Analogical Creativity

arXiv 2302.12832 ↗First posted 27 Feb 2023cs.CL cs.AIcited by 23

On the map: LLM reasoning → Reasoning benchmarks and evaluation

Abstract (arXiv)

Cross-domain analogical reasoning is a core creative ability that can be challenging for humans. Recent work has shown some proofs-of concept of Large language Models' (LLMs) ability to generate cross-domain analogies. However, the reliability and potential usefulness of this capacity for augmenting human creative work has received little systematic exploration. In this paper, we systematically explore LLMs capacity to augment cross-domain analogical reasoning. Across three studies, we found: 1) LLM-generated cross-domain analogies were frequently judged as helpful in the context of a problem reformulation task (median 4 out of 5 helpfulness rating), and frequently (~80% of cases) led to observable changes in problem formulations, and 2) there was an upper bound of 25% of outputs bring rated as potentially harmful, with a majority due to potentially upsetting content, rather than biased or toxic content. These results demonstrate the potential utility -- and risks -- of LLMs for augmenting cross-domain analogical creativity.

Key facts. Cited by 23 papers in the map (data through 7 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 21 of its 98 references that are in the map. First posted on arXiv 27 Feb 2023.

Builds on

21 of 98 references.

Closest ancestors · 1

Same direction, newest first

  1. 2022Emergent Analogical Reasoning in Large Language Models19 Dec

Other references · 20

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2022Training language models to follow instructions with human feedbackcited by 15,712
  3. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,346
  4. 2021Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processingcited by 2,222
  5. 2020Language (Technology) is Power: A Critical Survey of "Bias" in NLPcited by 951
  6. 2021Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigmcited by 599
  7. 2019The Woman Worked as a Babysitter: On Biases in Language Generationcited by 540
  8. 2021All That's 'Human' Is Not Gold: Evaluating Human Evaluation of Generated Textcited by 287
  9. 2020Social Biases in NLP Models as Barriers for Persons with Disabilitiescited by 182
  10. 2021Language Models are Few-shot Multilingual Learnerscited by 92
  11. 2022Evaluating Human-Language Model Interactioncited by 90
  12. 2021Sparks: Inspiration for Science Writing using Language Modelscited by 80
8 more
  1. 2021MERMAID: Metaphor Generation with Symbolism and Discriminative Decodingcited by 49
  2. 2017Accelerating Innovation Through Analogy Miningcited by 32
  3. 2022Analogy Generation by Prompting Large Language Models: A Case Study of InstructGPTcited by 27
  4. 2022Augmenting Scientific Creativity with an Analogical Search Enginecited by 22
  5. 2021Generative Pre-Trained Transformer for Design Concept Generation: An Explorationcited by 17
  6. 2022Biologically Inspired Design Concept Generation Using Generative Pre-Trained Transformerscited by 13
  7. 2017Evaluating vector-space models of analogycited by 6
  8. 2020Creativity on Paid Crowdsourcing Platformscited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 7; 2024: 10; 2025: 2; 2026: 4.

23 papers.

Sort:

By area:

  1. 2023Cognitive Mirage: A Review of Hallucinations in Large Language Modelscited by 83
  2. 2024Evolving Code with A Large Language Modelcited by 42
  3. 2024The Silicon Ceiling: Auditing GPT's Race and Gender Biases in Hiringcited by 29
  4. 2024Divergent Creativity in Humans and Large Language Modelscited by 29
  5. 2023StoryAnalogy: Deriving Story-level Analogies from Large Language Models to Unlock Analogical Understandingcited by 26
  6. 2024CS4: Measuring the Creativity of Large Language Models Automatically by Controlling the Number of Story-Writing Constraintscited by 22
  7. 2023Harnessing the Power of LLMs: Evaluating Human-AI Text Co-Creation through the Lens of News Headline Generationcited by 14
  8. 2025Co-Writing with AI, on Human Terms: Aligning Research with User Demands Across the Writing Processcited by 14
  9. 2023Beneath Surface Similarity: Large Language Models Make Reasonable Scientific Analogies after Structure Abductioncited by 11
  10. 2024AutoTRIZ: Automating Engineering Innovation with TRIZ and Large Language Modelscited by 8
  11. 2024Steering AI-Driven Personalization of Scientific Text for General Audiencescited by 7
  12. 2023Mapping the Design Space of Interactions in Human-AI Text Co-creation Taskscited by 6
11 more
  1. 2023Opportunities for Large Language Models and Discourse in Engineering Designcited by 6
  2. 2024"Like a Nesting Doll": Analyzing Recursion Analogies Generated by CS Students using Large Language Modelscited by 5
  3. 2023Elucidating STEM Concepts through Generative AI: A Multi-modal Exploration of Analogical Reasoningcited by 3
  4. 2024Boosting Scientific Concepts Understanding: Can Analogy from Teacher Models Empower Student Models?cited by 3
  5. 2024Frontend Diffusion: Exploring Intent-Based User Interfaces through Abstract-to-Detailed Task Transitionscited by 3
  6. 2026When AI Persuades: Adversarial Explanation Attacks on Human Trust in AI-Assisted Decision Makingcited by 2
  7. 2024Past Meets Present: Creating Historical Analogy with Large Language Modelscited by 1
  8. 2026Assessing the Effect of Cross-Domain Mapping on Creativity in Humans and Large Language Modelscited by 1
  9. 2025Accelerate Creation of Product Claims Using Generative AIcited by 0
  10. 2026Structural Ranking of the Cognitive Plausibility of Computational Models of Analogy and Metaphors with the Minimal Cognitive Gridcited by 0
  11. 2026Read, Grep, and Synthesize: Diagnosing Cross-Domain Seed Exposure for LLM Research Ideationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025CreativityPrism: A Cross-Domain Evaluation Framework for Large Language Model Creativity
  2. 2024AnaloBench: Benchmarking the Identification of Abstract and Long-context Analogies
  3. 2025A Causality-aware Paradigm for Evaluating Creativity of Multimodal Large Language Models
  4. 2026Can MLLMs Decode the Creative Leap? Introducing C4 for Cross-Concept Understanding
  5. 2025Modeling Understanding of Story-Based Analogies Using Large Language Models
  6. 2024Using Counterfactual Tasks to Evaluate the Generality of Analogical Reasoning in Large Language Models
  7. 2024LLMs as Models for Analogical Reasoning
  8. 2025Universe of Thoughts: Enabling Creative Reasoning with Large Language Models