LLMs generate valid solutions to over 70% of AI research problems from parametric memory alone but rediscover the exact published approach less than 19% of the time, with performance limited by cross-domain analogical transfer.
Advancing the scientific method with large language models: From hypothesis to discovery
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2025 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
The paper proposes a four-role framework for LLMs in scientific innovation and reviews methods, benchmarks, and limitations across Assistant, Collaborator, Scientist, and Evaluator roles.
citing papers explorer
-
AInstein: Can LLMs Solve Research Problems From Parametric Memory Alone?
LLMs generate valid solutions to over 70% of AI research problems from parametric memory alone but rediscover the exact published approach less than 19% of the time, with performance limited by cross-domain analogical transfer.
-
Evolving Roles of LLMs in Scientific Innovation: Assistant, Collaborator, Scientist, and Evaluator
The paper proposes a four-role framework for LLMs in scientific innovation and reviews methods, benchmarks, and limitations across Assistant, Collaborator, Scientist, and Evaluator roles.