Interesting Scientific Idea Generation using Knowledge Graphs and LLMs: Evaluations with 100 Research Group Leaders
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929664338952192 |
|---|---|
| author | Gu, Xuemei Krenn, Mario |
| author_facet | Gu, Xuemei Krenn, Mario |
| contents | The rapid growth of scientific literature makes it challenging for researchers to identify novel and impactful ideas, especially across disciplines. Modern artificial intelligence (AI) systems offer new approaches, potentially inspiring ideas not conceived by humans alone. But how compelling are these AI-generated ideas, and how can we improve their quality? Here, we introduce SciMuse, which uses 58 million research papers and a large-language model to generate research ideas. We conduct a large-scale evaluation in which over 100 research group leaders -- from natural sciences to humanities -- ranked more than 4,400 personalized ideas based on their interest. This data allows us to predict research interest using (1) supervised neural networks trained on human evaluations, and (2) unsupervised zero-shot ranking with large-language models. Our results demonstrate how future systems can help generating compelling research ideas and foster unforeseen interdisciplinary collaborations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_17044 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Interesting Scientific Idea Generation using Knowledge Graphs and LLMs: Evaluations with 100 Research Group Leaders Gu, Xuemei Krenn, Mario Artificial Intelligence Computation and Language Digital Libraries Machine Learning The rapid growth of scientific literature makes it challenging for researchers to identify novel and impactful ideas, especially across disciplines. Modern artificial intelligence (AI) systems offer new approaches, potentially inspiring ideas not conceived by humans alone. But how compelling are these AI-generated ideas, and how can we improve their quality? Here, we introduce SciMuse, which uses 58 million research papers and a large-language model to generate research ideas. We conduct a large-scale evaluation in which over 100 research group leaders -- from natural sciences to humanities -- ranked more than 4,400 personalized ideas based on their interest. This data allows us to predict research interest using (1) supervised neural networks trained on human evaluations, and (2) unsupervised zero-shot ranking with large-language models. Our results demonstrate how future systems can help generating compelling research ideas and foster unforeseen interdisciplinary collaborations. |
| title | Interesting Scientific Idea Generation using Knowledge Graphs and LLMs: Evaluations with 100 Research Group Leaders |
| topic | Artificial Intelligence Computation and Language Digital Libraries Machine Learning |
| url | https://arxiv.org/abs/2405.17044 |