Paper Detail
Mohammadhossein Khojasteh, Yifan Jiang, Stefano De Giorgis, Frank van Harmelen, Filip Ilievski
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.
No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.
No ranking explanation is available yet.
No tags.
@article{khojasteh2026enhancing,
title = {Enhancing Structural Mapping with LLM-derived Abstractions for Analogical Reasoning in Narratives},
author = {Mohammadhossein Khojasteh and Yifan Jiang and Stefano De Giorgis and Frank van Harmelen and Filip Ilievski},
year = {2026},
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},
url = {https://arxiv.org/abs/2603.29997},
keywords = {cs.CL, cs.AI},
eprint = {2603.29997},
archiveprefix = {arXiv},
}
{}