mlsanityData to 7 Oct 2026

Understanding Narratives through Dimensions of Analogy

arXiv 2206.07167 ↗First posted 14 Jun 2022cs.AI cs.CLcited by 7

On the map: LLM reasoning → Reasoning benchmarks and evaluation

Abstract (arXiv)

Analogical reasoning is a powerful qualitative reasoning tool that enables humans to connect two situations, and to generalize their knowledge from familiar to novel situations. Cognitive Science research provides valuable insights into the richness and complexity of analogical reasoning, together with implementations of expressive analogical reasoners with limited scalability. Modern scalable AI techniques with the potential to reason by analogy have been only applied to the special case of proportional analogy, and not to understanding higher-order analogies. In this paper, we aim to bridge the gap by: 1) formalizing six dimensions of analogy based on mature insights from Cognitive Science research, 2) annotating a corpus of fables with each of these dimensions, and 3) defining four tasks with increasing complexity that enable scalable evaluation of AI techniques. Experiments with language models and neuro-symbolic AI reasoners on these tasks reveal that state-of-the-art methods can be applied to reason by analogy with a limited success, motivating the need for further research towards comprehensive and scalable analogical reasoning by AI. We make all our code and data available.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 10 of its 53 references that are in the map. First posted on arXiv 14 Jun 2022.

Builds on

10 of 53 references.

References · 10

  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. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  4. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,346
  5. 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,243
  6. 2016The emotional arcs of stories are dominated by six basic shapescited by 69
  7. 2021BERT is to NLP what AlexNet is to CV: Can Pre-Trained Language Models Identify Analogies?cited by 56
  8. 2017Frame-Semantic Parsing with Softmax-Margin Segmental RNNs and a Syntactic Scaffoldcited by 33
  9. 2022Knowledge Base Question Answering by Case-based Reasoning over Subgraphscited by 31
  10. 2021Extracting Qualitative Causal Structure with Transformer-Based NLPcited by 2

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 3; 2024: 1; 2025: 2.

7 papers.

  1. 2023StoryAnalogy: Deriving Story-level Analogies from Large Language Models to Unlock Analogical Understandingcited by 26
  2. 2023ARN: Analogical Reasoning on Narrativescited by 8
  3. 2024Creativity in AI: Progresses and Challengescited by 7
  4. 2025Modelling Analogies and Analogical Reasoning: Connecting Cognitive Science Theory and NLP Researchcited by 3
  5. 2023Transferring Procedural Knowledge across Commonsense Taskscited by 2
  6. 2022Does Wikidata Support Analogical Reasoning?cited by 1
  7. 2025Analogical Structure, Minimal Contextual Cues and Contrastive Distractors: Input Design for Sample-Efficient Linguistic Rule Inductioncited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2023In-Context Analogical Reasoning with Pre-Trained Language Models
  2. 2025The Curious Case of Analogies: Investigating Analogical Reasoning in Large Language Models
  3. 2024LLMs as Models for Analogical Reasoning
  4. 2022Emergent Analogical Reasoning in Large Language Models
  5. 2026Enhancing Structural Mapping with LLM-derived Abstractions for Analogical Reasoning in Narratives
  6. 2024AnaloBench: Benchmarking the Identification of Abstract and Long-context Analogies
  7. 2026When Models Know More Than They Say: Probing Analogical Reasoning in LLMs
  8. 2025Modeling Understanding of Story-Based Analogies Using Large Language Models