# Enhancing multimodal analogical reasoning with Logic Augmented Generation

arXiv: https://arxiv.org/abs/2504.11190 · HTML: https://mlsanity.com/paper/2504.11190/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 17 of its 79 references that are in the map.
- First posted on arXiv 15 Apr 2025.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 17 of 17)

- [BLEURT: Learning Robust Metrics for Text Generation](https://mlsanity.com/paper/2004.04696/) (2020)
- [Measuring Compositional Generalization: A Comprehensive Method on Realistic Data](https://mlsanity.com/paper/1912.09713/) (2019)
- [Emergent Analogical Reasoning in Large Language Models](https://mlsanity.com/paper/2212.09196/) (2022)
- [Compositional Generalization in Semantic Parsing: Pre-training vs. Specialized Architectures](https://mlsanity.com/paper/2007.08970/) (2020)
- [The Next Chapter: A Study of Large Language Models in Storytelling](https://mlsanity.com/paper/2301.09790/) (2023)
- [Word meaning in minds and machines](https://mlsanity.com/paper/2008.01766/) (2020)
- [Metaphor Generation with Conceptual Mappings](https://mlsanity.com/paper/2106.01228/) (2021)
- [I Spy a Metaphor: Large Language Models and Diffusion Models Co-Create Visual Metaphors](https://mlsanity.com/paper/2305.14724/) (2023)
- [MetaCLUE: Towards Comprehensive Visual Metaphors Research](https://mlsanity.com/paper/2212.09898/) (2022)
- [FrameBERT: Conceptual Metaphor Detection with Frame Embedding Learning](https://mlsanity.com/paper/2302.04834/) (2023)
- [A Sentence is Worth a Thousand Pictures: Can Large Language Models Understand Hum4n L4ngu4ge and the W0rld behind W0rds?](https://mlsanity.com/paper/2308.00109/) (2023)
- [Do large language models solve verbal analogies like children do?](https://mlsanity.com/paper/2310.20384/) (2023)
- [ANALOGICAL -- A Novel Benchmark for Long Text Analogy Evaluation in Large Language Models](https://mlsanity.com/paper/2305.05050/) (2023)
- [Amnestic Forgery: an Ontology of Conceptual Metaphors](https://mlsanity.com/paper/1805.12115/) (2018)
- [Neurosymbolic Graph Enrichment for Grounded World Models](https://mlsanity.com/paper/2411.12671/) (2024)
- [Science is Exploration: Computational Frontiers for Conceptual Metaphor Theory](https://mlsanity.com/paper/2410.08991/) (2024)
- [Logic Augmented Generation](https://mlsanity.com/paper/2411.14012/) (2024)

## Built on by (most cited first, 1 of 1)

- [Meanings are like Onions: a Layered Approach to Metaphor Processing](https://mlsanity.com/paper/2507.10354/) (2025)

## Abstract (arXiv)

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.