# Enhancing multimodal analogical reasoning with Logic Augmented Generation

Source: [Enhancing multimodal analogical reasoning with Logic Augmented Generation](<https://www.sota2.com/research/paper/68fa79591e209131cea7d349>)

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

Data updated: 2026-03-07T05:00:10.880Z

Authors: Anna Sofia Lippolis, Andrea Giovanni Nuzzolese, Aldo Gangemi

Published: 2025-04-15T13:47:55.000Z

## Abstract

Recent advances in Large Language Models have demonstrated their capabilities across a variety of tasks. However, automatically extracting implicit knowledge from natural language remains a significant challenge, as machines lack active experience with the physical world. Given this scenario, semantic knowledge graphs can serve as conceptual spaces that guide the automated text generation reasoning process to achieve more efficient and explainable results. In this paper, we apply a logic-augmented generation (LAG) framework that leverages the explicit representation of a text through a semantic knowledge graph and applies it in combination with prompt heuristics to elicit implicit analogical connections. This method generates extended knowledge graph triples representing implicit meaning, enabling systems to reason on unlabeled multimodal data regardless of the domain. We validate our work through three metaphor detection and understanding tasks across four datasets, as they require deep analogical reasoning capabilities. The results show that this integrated approach surpasses current baselines, performs better than humans in understanding visual metaphors, and enables more explainable reasoning processes, though still has inherent limitations in metaphor understanding, especially for domain-specific metaphors. Furthermore, we propose a thorough error analysis, discussing issues with metaphorical annotations and current evaluation methods.

## 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.

- [Metaphor detection on MOH-X](<https://www.sota2.com/research/sota/metaphor-detection-on-moh-x.md>): Metaphor Detection; MOH-X; F1 Score: 89.7.

- [Metaphor Detection on TroFi](<https://www.sota2.com/research/sota/metaphor-detection-on-trofi.md>): Metaphor Detection; TroFi; F1 Score: 89.7.

- [Metaphor Detection on BCTMD](<https://www.sota2.com/research/sota/metaphor-detection-on-bctmd.md>): Metaphor Detection; BCTMD; Accuracy: 80.1.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2504.11190>)

[PDF](<https://arxiv.org/pdf/2504.11190.pdf>)
