Date
AI Overview
Why it matters
Large language models can reshape research workflows and practice across disciplines, but researchers need an integrated understanding of current capabilities, trade-offs, and failure modes to use them effectively and responsibly.
Study at a glance
- Question: How are large language models applied across academic disciplines, and what are their key strengths and limitations?
- Setting and data: Literature, benchmarks, and model performance data across arts and humanities, social sciences, business, and STEM disciplines through 2025.
- Method: Comprehensive cross-disciplinary literature review and benchmark synthesis.
- AI tools: GPT-4o, Claude 3.7 Sonnet, DeepSeek-R1, Gemini 2.0 Flash, Grok 3, Llama 3.3
Key findings
- No single model dominates across all domains, as general conversational systems excel on dialogue while specialized or reasoning models perform best on mathematics, code, and structured logic.
- Across disciplines, models struggle with deep causal reasoning, long-range temporal understanding, hallucinations, and domain-specific physical or numerical constraints.
- In educational applications such as mathematics, student learning gains are highest when learners attempt problems first before consulting model-generated explanations rather than viewing answers immediately.
Summary drafted with AI from the full paper and may contain errors. See the full paper for details.
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.
Research Categories
What is the application?
Who age?
Study design
AI tools
Publication Source
Publisher
arXiv
