Large language models surpass human experts in predicting neuroscience results | Nature Human Behaviour
Large language models (LLMs) can synthesize vast amounts of information. Luo et al. show that LLMs—especially BrainGPT, an LLM the authors tuned on the neuroscience literature—outperform experts in predicting neuroscience results and could assist scientists in making future discoveries.
Main Keeping up with the exponentially increasing1 scientific literature is a superhuman challenge. Potentially disruptive findings go unnoticed in the deluge of articles2. Processing and integrating the myriad of relevant findings may already surpass humans’ abilities. One path forward involves human scientists leveraging advanced machines. This approach could take several forms, including specialist solutions that address specific challenges, such as in protein folding3, drug discovery4 and materials science5. Alternatively, general models of the scientific literature could help guide…
saved by
related reading
- Language models can explain neurons in language modelsopenaipublic.blob.core.windows.net
- Language Models, World Models, and Human Model-Buildinglingo.csail.mit.edu
- [2005.14165] Language Models are Few-Shot Learnersarxiv.org
- Large Language Model: world models or surface statistics?thegradient.pub
- 2301.06627arxiv.org
- Predicting Empirical AI Research Outcomes with Language Modelsarxiv.org
- Do large language models understand us? | by Blaise Aguera y Arcas | Mediummedium.com
- Trading places: What happens when neuroscience turns into machine learning, and machine learning turns into neuroscience?thetransmitter.org
- Language Models in Plato's Cave - by Sergey Levinesergeylevine.substack.com
- High-level visual representations in the human brain are aligned with large language models | Nature Machine Intelligencenature.com
- Large Language Models Must Be Taught to Know What They Don't Knowarxiv.org
- [2301.06627] Dissociating language and thought in large language models: a cognitive perspectivearxiv.org