metadata
base_model:
- mistralai/Mistral-7B-Instruct-v0.3
datasets:
- noystl/Recombination-Extraction
language:
- en
license: cc-by-4.0
metrics:
- accuracy
pipeline_tag: feature-extraction
library_name: transformers
This Hugging Face repository hosts a fine-tuned Mistral model designed to classify scientific abstracts based on whether they involve idea recombination, as introduced in the paper CHIMERA: A Knowledge Base of Idea Recombination in Scientific Literature. The model employs a LoRA adapter on top of a Mistral base model.
For detailed usage instructions and to reproduce the results, please refer to the linked GitHub repository.
Bibtex
@misc{sternlicht2025chimeraknowledgebaseidea,
title={CHIMERA: A Knowledge Base of Idea Recombination in Scientific Literature},
author={Noy Sternlicht and Tom Hope},
year={2025},
eprint={2505.20779},
archivePrefix={arXiv},
primaryClass={cs.CL},
url={https://arxiv.org/abs/2505.20779},
}
Quick Links