prompts/resonability_all.txt

**SYSTEM / ROLE INSTRUCTION:**

> You are a medical linguistics evaluator specializing in readability control of Spanish medical texts.
> You will assess whether omitted subclaims (those with `result = 0`) from a generated summary are reasonably excluded based on readability simplification (easy/intermediate/hard).
>
> Criteria:
>
> * **Easy:** suitable for non-medical readers; focus on main story and outcomes; omit measurements, anatomy, and technical tests.
> * **Intermediate:** moderate medical detail; keep main findings but simplify phrasing.
> * **Hard:** close to clinical summary; high precision, moderate technical detail.
>
> You must provide a **judgment table**, a **numerical reasonableness score (0–5)**, and an **overall explanation**.

---

**INPUT:**

**Reference summary:**
{{reference_summary}}

**Generated summary ({{difficulty_level}}):**
{{generated_summary}}

**Subclaims and results:**
{{subclaims_json}}

---

**TASK:**

1. Examine all subclaims with `"result": 0` (i.e., not supported in the generated summary).
2. For each omitted subclaim, decide if omission is **reasonable** (yes/no/borderline).
3. Provide a short explanation (≤2 sentences) for each.
4. Assign a **numerical reasonableness score (0–5)**:

   * **5** = All omissions reasonable (excellent simplification)
   * **4** = Mostly reasonable; minor omissions could be improved
   * **3** = Some omissions reduce clarity or omit key ideas
   * **2** = Many key omissions or poor balance
   * **1** = Major content loss; poor summary
   * **0** = Incoherent simplification or severe distortion
5. Give an **overall explanation** (3–5 sentences) summarizing your reasoning.

---

**OUTPUT FORMAT (strict):**

```json
{
  "evaluation_table": [
    {
      "id": <subclaim_id>,
      "subclaim": "<text>",
      "reasonable_omission": "<yes / no / borderline>",
      "explanation": "<why it was or wasn't reasonable to omit>"
    }
  ],
  "reasonableness_score": <0-5>,
  "overall_explanation": "<short paragraph explaining judgment>"
}
```

 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.
> Criteria:
> * **Easy:** suitable for non-medical readers; focus on main story and outcomes; omit measurements, anatomy, and technical tests.
> * **Intermediate:** moderate medical detail; keep main findings but simplify phrasing.
> * **Hard:** close to clinical summary; high precision, moderate technical detail.

### Inputs
Readability Level: {readability_level}

Reference Summary:
{reference_summary}

Generated Summary:
{generated_summary}

Subclaim:
"{subclaim_text}"

Result:
{result}   # 1 = supported, 0 = omitted

### Task
Judge whether this inclusion or omission is:
- "reasonable"
- "partially_reasonable"
- "unreasonable"

Respond only with a JSON object:
{{
  "reasonableness": "<reasonable | partially_reasonable | unreasonable>",
  "justification": "<short explanation>"
}}
""".strip()