Spectral Neuro-Symbolic Reasoning II: Semantic Node Merging, Entailment Filtering, and Knowledge Graph Alignment

This paper investigates the automated classification of exam questions and learning outcomes based on Bloom's Taxonomy. A dataset of 600 sentences was categorized into six cognitive levels: Knowledge, Comprehension, Application, Analysis, Synthesis, and Evaluation. Various machine learning models, including traditional methods and large language models, were evaluated, with Support Vector Machines achieving the highest accuracy of 94%, while RNN models and BERT faced significant overfitting issues.

The study examines the performance of pretrained transformer-encoder models, specifically ModernBERT and DeBERTaV3. While ModernBERT claims improved performance on various benchmarks, the lack of shared training data complicates the assessment of these gains. A controlled study pretraining ModernBERT on the same dataset as CamemBERTaV2 reveals that DeBERTaV3 outperforms ModernBERT in sample efficiency and overall benchmark performance, although ModernBERT offers advantages in long context support and training speed.

The article examines the balance between generalization and memorization in text-to-image diffusion models, focusing on 'multimodal iconicity.' This concept refers to how images and texts evoke shared cultural associations. The authors introduce an evaluation framework that distinguishes between recognition of cultural references and their realization in images. They evaluate five diffusion models against 767 cultural references from Wikidata, demonstrating their framework's ability to differentiate between replication and transformation.