LLMs4All: A Review on Large Language Models for Research and Applications in Academic Disciplines

2025-09-23

AI Summary

This study addresses the fragmented and unsystematic application of large language models (LLMs) across disciplines. We conduct the first systematic, cross-domain review spanning humanities, social sciences, and engineering. Employing bibliometric analysis and in-depth case studies of representative applications, we integrate generative AI, natural language processing, and domain-specific knowledge modeling to map LLM research advances and practical bottlenecks in art, law, economics, and science. Our primary contribution is the proposal of the first comprehensive, discipline-agnostic LLM application framework—articulating technology adaptation pathways, discipline-specific challenges (e.g., interpretability in law, creativity evaluation in art), and multi-stakeholder governance mechanisms. We further distill reusable domain-adaptation paradigms and evidence-based development recommendations, grounded in empirical findings. This work provides both a theoretical foundation and actionable guidance for researchers and practitioners seeking rigorous, context-aware LLM deployment across academic domains.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Application Domains: Humanities & Computational Social Science
• Natural Language Processing: (Large) Language Models

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

Cutting-edge Artificial Intelligence (AI) techniques keep reshaping our view of the world. For example, Large Language Models (LLMs) based applications such as ChatGPT have shown the capability of generating human-like conversation on extensive topics. Due to the impressive performance on a variety of language-related tasks (e.g., open-domain question answering, translation, and document summarization), one can envision the far-reaching impacts that can be brought by the LLMs with broader real-world applications (e.g., customer service, education and accessibility, and scientific discovery). Inspired by their success, this paper will offer an overview of state-of-the-art LLMs and their integration into a wide range of academic disciplines, including: (1) arts, letters, and law (e.g., history, philosophy, political science, arts and architecture, law), (2) economics and business (e.g., finance, economics, accounting, marketing), and (3) science and engineering (e.g., mathematics, physics and mechanical engineering, chemistry and chemical engineering, life sciences and bioengineering, earth sciences and civil engineering, computer science and electrical engineering). Integrating humanity and technology, in this paper, we will explore how LLMs are shaping research and practice in these fields, while also discussing key limitations, open challenges, and future directions in the era of generative AI. The review of how LLMs are engaged across disciplines-along with key observations and insights-can help researchers and practitioners interested in exploiting LLMs to advance their works in diverse real-world applications.

Problem

• Reviewing state-of-the-art LLMs integration across academic disciplines
• Exploring how LLMs shape research and practice in various fields
• Discussing limitations, challenges and future directions of generative AI

Innovation

• Reviewing state-of-the-art LLMs across academic disciplines
• Exploring LLM integration in arts, business, and science
• Discussing limitations and future directions of generative AI