# Enhancing Structural Mapping with LLM-derived Abstractions for Analogical Reasoning in Narratives

Source: [Enhancing Structural Mapping with LLM-derived Abstractions for Analogical Reasoning in Narratives](<https://www.sota2.com/research/paper/69cca6ad0636e5bf4afcbcfd>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-04-02T05:00:12.805Z

Authors: Mohammadhossein Khojasteh, Yifan Jiang, Stefano De Giorgis, Frank van Harmelen, Filip Ilievski

Published: 2026-03-31T16:57:11.000Z

## Abstract

Analogical reasoning is a key driver of human generalization in problem-solving and argumentation. Yet, analogies between narrative structures remain challenging for machines. Cognitive engines for structural mapping are not directly applicable, as they assume pre-extracted entities, whereas LLMs' performance is sensitive to prompt format and the degree of surface similarity between narratives. This gap motivates a key question: What is the impact of enhancing structural mapping with LLM-derived abstractions on their analogical reasoning ability in narratives? To that end, we propose a modular framework named YARN (Yielding Abstractions for Reasoning in Narratives), which uses LLMs to decompose narratives into units, abstract these units, and then passes them to a mapping component that aligns elements across stories to perform analogical reasoning. We define and operationalize four levels of abstraction that capture both the general meaning of units and their roles in the story, grounded in prior work on framing. Our experiments reveal that abstractions consistently improve model performance, resulting in competitive or better performance than end-to-end LLM baselines. Closer error analysis reveals the remaining challenges in abstraction at the right level, in incorporating implicit causality, and an emerging categorization of analogical patterns in narratives. YARN enables systematic variation of experimental settings to analyze component contributions, and to support future work, we make the code for YARN openly available.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Analogical Reasoning on MCQ](<https://www.sota2.com/research/sota/analogical-reasoning-on-mcq.md>): Analogical Reasoning; MCQ; Accuracy: 46.

- [Analogical Reasoning on ARN Far Analogy](<https://www.sota2.com/research/sota/analogical-reasoning-on-arn-far-analogy.md>): Analogical Reasoning; ARN Far Analogy; Accuracy: 47.

- [Analogical Reasoning on ARN Near Analogy](<https://www.sota2.com/research/sota/analogical-reasoning-on-arn-near-analogy.md>): Analogical Reasoning; ARN Near Analogy; Accuracy: 73.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2603.29997>)

[PDF](<https://arxiv.org/pdf/2603.29997.pdf>)
