An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.
Python agentic-ragdeep-researchemnlp2024knowledge-curationlarge-language-modelsnaaclnlpreport-generationretrieval-augmented-generation
fixed typo in example readme
AMMAS142dfbbb6959d
diff --git a/examples/README.md b/examples/README.mdindex eb4da9b..6aa04a3 100644--- a/examples/README.md+++ b/examples/README.md@@ -83,7 +83,7 @@ By default, STORM is grounded on the Internet using the search engine, but it ca- Run the following command under the root directory to downsample the dataset by filtering papers with terms `[cs.CV]` and get a csv file that match the format mentioned above.```- python examples/helper/process_kaggle_arxiv_abstract_dataset --input-path $PATH_TO_THE_DOWNLOADED_FILE --output-path $PATH_TO_THE_PROCESSED_CSV+ python examples/helper/process_kaggle_arxiv_abstract_dataset.py --input-path $PATH_TO_THE_DOWNLOADED_FILE --output-path $PATH_TO_THE_PROCESSED_CSV```- Run the following command to run STORM grounding on the processed dataset. You can input a topic related to computer vision (e.g., "The progress of multimodal models in computer vision") to see the generated article. (Note that the generated article may not include enough details since the quick test only use the abstracts of arxiv papers.)