Minseok Bae
Modified for hallucination evaluation task
d7b7dc6
raw
history blame
1.25 kB
import pandas as pd
def load_dataframe(data_path):
df = pd.read_csv(data_path)
return df
def generate_prompt(source_passage):
return f"""You are a chat bot answering questions using data. You must stick to the answers provided solely by the text in the passage provided.
You are asked the question 'Provide a concise summary of the following passage, covering the core pieces of information described.'
Passage:
{source_passage}
"""
def format_results(hallucination_scores, model_name, revision, precision, accuracy, hallucination_rate, answer_rate, avg_summary_len):
# Define the structure of the results (JSON)
results = {
"config": {
"model_dtype": precision, # Precision with which you ran the evaluation
"model_name": model_name, # Name of the model
"model_sha": revision # Hash of the model
},
"results": {
"hallucination_eval": {
"HEM Scores": hallucination_scores,
"Accuracy": accuracy,
"Hallucination Rate": hallucination_rate,
"Answer Rate": answer_rate,
"Average Summary Length": avg_summary_len,
}
}
}
return results