Transforming Science with Large Language Models: A Survey on AI-assisted Scientific Discovery, Experimentation, Content Generation, and Evaluation

TL;DR

This survey reviews how large multimodal language models are transforming scientific research by supporting tasks from literature search to experiment generation, content creation, and evaluation, highlighting techniques, challenges, and ethical issues.

Contribution

It provides a comprehensive overview of AI techniques and trends across the entire scientific workflow, serving as a guide for future AI-driven scientific systems.

Findings

AI models assist in literature search and idea generation

Multimodal models enable creation of scientific figures and diagrams

Evaluation practices and ethical concerns are critically discussed

Abstract

With the advent of large multimodal language models, science is now at a threshold of an AI-based technological transformation. An emerging ecosystem of models and tools aims to support researchers throughout the scientific lifecycle, including (1) searching for relevant literature, (2) generating research ideas and conducting experiments, (3) producing text-based content, (4) creating multimodal artifacts such as figures and diagrams, and (5) evaluating scientific work, as in peer review. In this survey, we provide a curated overview of literature representative of the core techniques, evaluation practices, and emerging trends in AI-assisted scientific discovery. Across the five tasks outlined above, we discuss datasets, methods, results, evaluation strategies, limitations, and ethical concerns, including risks to research integrity through the misuse of generative models. We aim for this survey to serve both as an accessible, structured orientation for newcomers to the field, as well as a catalyst for new AI-based initiatives and their integration into future ``AI4Science'' systems.