mlsanityData to 7 Oct 2026

Boosting Scientific Concepts Understanding: Can Analogy from Teacher Models Empower Student Models?

arXiv 2406.11375 ↗First posted 17 Jun 2024cs.CL cs.AIcited by 3

On the map: LLM reasoning → Reasoning benchmarks and evaluation

Abstract (arXiv)

Analogical reasoning plays a critical role in human cognition, enabling us to understand new concepts by associating them with familiar ones. Previous research in the AI community has mainly focused on identifying and generating analogies and then examining their quality under human evaluation, which overlooks the practical application of these analogies in real-world settings. Inspired by the human education process, in this paper, we propose to investigate how analogies created by teacher language models (LMs) can assist student LMs in understanding scientific concepts, thereby aligning more closely with practical scenarios. Our results suggest that free-form analogies can indeed aid LMs in understanding concepts. Additionally, analogies generated by student LMs can improve their own performance on scientific question answering, demonstrating their capability to use analogies for self-learning new knowledge. Resources are available at https://github.com/siyuyuan/SCUA.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 19 of its 40 references that are in the map. First posted on arXiv 17 Jun 2024.

Builds on

19 of 40 references.

Closest ancestors · 5

Same direction, newest first

  1. 2023Beneath Surface Similarity: Large Language Models Make Reasonable Scientific Analogies after Structure Abduction22 May
  2. 2023ANALOGYKB: Unlocking Analogical Reasoning of Language Models with A Million-scale Knowledge Base10 May
  3. 2023Fluid Transformers and Creative Analogies: Exploring Large Language Models' Capacity for Augmenting Cross-Domain Analogical Creativity27 Feb
  4. 2022PINTO: Faithful Language Reasoning Using Prompt-Generated Rationales3 Nov
  5. 2022E-KAR: A Benchmark for Rationalizing Natural Language Analogical Reasoning16 Mar

Other references · 14

  1. 2018Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challengecited by 4,710
  2. 2023GPQA: A Graduate-Level Google-Proof Q&A Benchmarkcited by 2,748
  3. 2023Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizescited by 710
  4. 2021Abstraction and Analogy-Making in Artificial Intelligencecited by 103
  5. 2023SCOTT: Self-Consistent Chain-of-Thought Distillationcited by 103
  6. 2019Analogies Explained: Towards Understanding Word Embeddingscited by 63
  7. 2021BERT is to NLP what AlexNet is to CV: Can Pre-Trained Language Models Identify Analogies?cited by 56
  8. 2022Analogy Generation by Prompting Large Language Models: A Case Study of InstructGPTcited by 27
  9. 2023StoryAnalogy: Deriving Story-level Analogies from Large Language Models to Unlock Analogical Understandingcited by 26
  10. 2022Augmenting Scientific Creativity with an Analogical Search Enginecited by 22
  11. 2022Life is a Circus and We are the Clowns: Automatically Finding Analogies between Situations and Processescited by 22
  12. 2020Analogies minus analogy test: measuring regularities in word embeddingscited by 17
2 more
  1. 2024AnaloBench: Benchmarking the Identification of Abstract and Long-context Analogiescited by 13
  2. 2024ParallelPARC: A Scalable Pipeline for Generating Natural-Language Analogiescited by 8

Built on by

Cited by year

Citing papers per year: 2024: 1; 2025: 2.

3 papers.

  1. 2025Training Turn-by-Turn Verifiers for Dialogue Tutoring Agents: The Curious Case of LLMs as Your Coding Tutorscited by 17
  2. 2025Understanding LLM Scientific Reasoning through Promptings and Model's Explanation on the Answerscited by 10
  3. 2024Hybrid Student-Teacher Large Language Model Refinement for Cancer Toxicity Symptom Extractioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Modeling Understanding of Story-Based Analogies Using Large Language Models
  2. 2025Modelling Analogies and Analogical Reasoning: Connecting Cognitive Science Theory and NLP Research
  3. 2024LLMs as Models for Analogical Reasoning
  4. 2023Can language models learn analogical reasoning? Investigating training objectives and comparisons to human performance
  5. 2024Relevant or Random: Can LLMs Truly Perform Analogical Reasoning?
  6. 2025The Curious Case of Analogies: Investigating Analogical Reasoning in Large Language Models
  7. 2022Scientific and Creative Analogies in Pretrained Language Models
  8. 2024Evaluating the Robustness of Analogical Reasoning in Large Language Models