IDEAL: Leveraging Infinite and Dynamic Characterizations of Large Language Models for Query-focused Summarization

1. Download datasets from their respective official repositories:

   • SQuALITY
   • CovidET
   • QMSum

2. Preprocess the datasets using the provided Jupyter notebook: data_process.ipynb.

To train, run inference, and evaluate the model, execute the following script:

bash exps/finetuning_*_generate_evaluate.sh

For multi-reference Rouge scores and Bart-score evaluations on the SQuALITY dataset, use the notebook multi_reference_evaluation_SQuAlITY.ipynb.