prompts/resonability_prompt.txt

def readability_judgment_single_prompt(reference_summary, generated_summary, readability_level, subclaim_text, result, evaluation):
    system_prompt = f"""
You are an impartial medical summarization evaluator.

Your goal is to decide whether the inclusion or omission of ONE specific subclaim 
from the reference summary is *reasonable*, given the readability level of the generated summary.

Readability guidelines:
- Easy: for general readers; omit detailed numbers, anatomy, or diagnostic test specifics.
- Intermediate: maintain main medical ideas and reasoning; simplify complex phrasing only.
- Hard: preserve nearly all technical and diagnostic detail, except redundant measurements.

### Inputs
Readability Level: {readability_level}

Reference Summary:
{reference_summary}

Generated Summary:
{generated_summary}

Subclaim:
"{subclaim_text}"

Result:
{result}   # 1 = supported (included in generated summary), 0 = omitted (not included)

### Consistency rules:
* If result = 0 (omitted) and the subclaim is purely technical or numerical for this readability level, likely "reasonable".
* If result = 0 and the subclaim expresses a central event, diagnosis, or reason for treatment outcome, mark "unreasonable".

### Task
Judge whether this inclusion or omission is:
- "reasonable" → appropriate for this readability level
- "partially_reasonable" → oversimplified but acceptable
- "unreasonable" → harms completeness or clinical meaning

Output format rule: produce exactly the JSON object below, no extra commentary.

{{
  "reasonableness": "<reasonable | partially_reasonable | unreasonable>",
  "justification": "<short explanation>"
}}
"""

    conversation = {}
    conversation['conversations'] = (
        {'from': "user", 'content': system_prompt},
        {'from': "assistant", 'content': str(evaluation)},
    )
    return conversation