Can llms generate novel research ideas? a large-scale human study with 100+ nlp researchers

C Si, D Yang, T Hashimoto - arXiv preprint arXiv:2409.04109, 2024 - arxiv.org
Recent advancements in large language models (LLMs) have sparked optimism about their
potential to accelerate scientific discovery, with a growing number of works proposing …

The Shadow of Fraud: The Emerging Danger of AI-powered Social Engineering and its Possible Cure

J Yu, Y Yu, X Wang, Y Lin, M Yang, Y Qiao… - arXiv preprint arXiv …, 2024 - arxiv.org
Social engineering (SE) attacks remain a significant threat to both individuals and
organizations. The advancement of Artificial Intelligence (AI), including diffusion models and …

The Promise and Perils of Autonomous AI in Science

J Gao, EM Harrison - NEJM AI, 2025 - ai.nejm.org
In this edition of NEJM AI, Ifargan and colleagues present data-to-paper, an autonomous
platform designed to mimic human scientific practice by guiding a large language model …

CoEvo: Continual Evolution of Symbolic Solutions Using Large Language Models

P Guo, Q Zhang, X Lin - arXiv preprint arXiv:2412.18890, 2024 - arxiv.org
Large Language Models (LLMs) have emerged as transformative tools in artificial
intelligence, capable of processing and understanding extensive human knowledge to …

Creativity in AI: Progresses and Challenges

M Ismayilzada, D Paul, A Bosselut… - arXiv preprint arXiv …, 2024 - arxiv.org
Creativity is the ability to produce novel, useful, and surprising ideas, and has been widely
studied as a crucial aspect of human cognition. Machine creativity on the other hand has …

Autonomous self-evolving research on biomedical data: the DREAM paradigm

L Deng, Y Wu, Y Ren, H Lu - arXiv preprint arXiv:2407.13637, 2024 - arxiv.org
In contemporary biomedical research, the efficiency of data-driven approaches is hindered
by large data volumes, tool selection complexity, and human resource limitations …

Agent Laboratory: Using LLM Agents as Research Assistants

S Schmidgall, Y Su, Z Wang, X Sun, J Wu, X Yu… - arXiv preprint arXiv …, 2025 - arxiv.org
Historically, scientific discovery has been a lengthy and costly process, demanding
substantial time and resources from initial conception to final results. To accelerate scientific …

Large Language Models RePower Autonomous Research of Data-Driven Tasks in Power Systems

YX Liu, M Jia, YX Zhang, J Wang, G He, S Zhong… - 2024 - research-collection.ethz.ch
Large language models (LLMs) have demonstrated exceptional performance across various
fields, including chemistry, mathematics, medical science, and materials science. However …

[PDF][PDF] Tutorial Proposal: Causality for Large Language Models

Z Jin, S Garrido - zhijing-jin.com
In this tutorial, we will explore the intersection of causality and large language models
(LLMs). Our goal is to provide a comprehensive understanding of how causal inference can …

[PDF][PDF] Autonomous Generalist Scientist: Towards and Beyond Human-level Automatic Research Using Foundation Model-Based AI Agents and Robots (A Position)

S Zhang, A Pearson, Z Wang - researchgate.net
The accelerating pace of scientific research highlights the need for more efficient, accurate,
and comprehensive methodologies. Traditional research methods are often hindered by the …