arXiv:2510.16152v2 Announce Type: replace-cross 
Abstract: Scientific literature is increasingly fragmented by disciplinary boundaries, specialized terminology, and potentially sparse keyword systems, making it difficult to capture the evolving structure of modern science. This study introduces a large language model (LLM)-driven framework for mapping scientific literature from a topic modeling perspective. The approach is demonstrated on a 20-year corpus of more than 1,500 engineering-related articles published in the Proceedings of the National Academy of Sciences (PNAS). A two-stage classification pipeline first assigns a primary thematic category to each article based on its abstract, followed by full-text analysis to identify secondary classifications that reveal latent cross-topic connections within the corpus. Unlike conventional topic models, the LLM-based framework produces semantically interpretable topics while maintaining strong quantitative performance. Comparative evaluation against established topic modeling methods shows higher topic diversity and lower overlap with competitive coherence metrics. Manual validation on a randomly sampled subset of abstracts yields an accuracy of 75.9%. Additional traditional natural language processing analyses confirm that the generated topics correspond to meaningful linguistic patterns in the corpus. A bipartite network linking primary and secondary classifications further reveals implicit thematic relationships that are not readily observable through abstracts or keyword systems alone. The findings indicate that the framework independently recovers much of the journal's editorial dual-classification structure without prior knowledge of its schema. Overall, the proposed approach offers a powerful tool for mapping science and identifying emerging cross-topic connections in research.

تم تقديم إطار عمل جديد يعتمد على نماذج اللغة الكبيرة (LLMs) لرسم خريطة الأدب العلمي، مع التركيز بشكل خاص على مجموعة بيانات تمتد لعشرين عامًا تضم أكثر من 1500 مقال في الهندسة نُشرت في وقائع الأكاديمية الوطنية للعلوم (PNAS). تستخدم هذه الطريقة خط أنابيب تصنيف من مرحلتين لتصنيف المقالات موضوعيًا وتحديد الروابط الكامنة بين المواضيع.

Se ha introducido un nuevo marco que utiliza modelos de lenguaje de gran tamaño (LLMs) para mapear la literatura científica, centrándose específicamente en un corpus de 20 años de más de 1,500 artículos de ingeniería publicados en las Actas de la Academia Nacional de Ciencias (PNAS). Este enfoque utiliza un pipeline de clasificación en dos etapas para categorizar los artículos temáticamente e identificar conexiones latentes entre los temas.

Un nouveau cadre utilisant des modèles de langage de grande taille (LLMs) a été introduit pour cartographier la littérature scientifique, en se concentrant spécifiquement sur un corpus de 20 ans de plus de 1 500 articles d'ingénierie publiés dans les Actes de l'Académie nationale des sciences (PNAS). Cette approche utilise un pipeline de classification en deux étapes pour catégoriser les articles thématiquement et identifier les connexions latentes entre les sujets.

A new framework leveraging large language models (LLMs) has been introduced to map scientific literature, specifically focusing on a 20-year corpus of over 1,500 engineering articles from the Proceedings of the National Academy of Sciences (PNAS). This approach utilizes a two-stage classification pipeline to categorize articles thematically and identify latent connections across topics.