
# Step 1: Navigate to the run_script directory
cd run_script

# Step 2: Run the test using run.sh
# Replace [model_names], [path_to_test_file], and [path_to_output_file] with your actual values
bash run.sh [model_names] [path_to_test_file] [path_to_output_file]

# Step 3: (For FuseEval dataset only)
# Edit evaluate_score.sh to set the correct path to your test output file
# Then run the script to calculate evaluation metrics
bash evaluate_score.sh



A more detailed version of the code will be released on GitHub after the paper is accepted.