予期しない出力を診断する

# Example: wrong answer failure
prompt = 'What year was Python first released?'
response = 'Python was first released in 1994.'  # Wrong — it was 1991

# Ground truth check
GROUND_TRUTH = '1991'
correct = GROUND_TRUTH in response
print(f'Correct: {correct}')  # False

import json

response_text = 'Sure! Here is the result: {"name": "Alice", "age": 30}'

try:
    data = json.loads(response_text)
    print('Format OK:', data)
except json.JSONDecodeError as e:
    print(f'FORMAT FAILURE: {e}')
    # 'Sure! Here is the result:' prefix broke JSON parsing

# Off-topic example
prompt = 'Write a Python function that reverses a list.'
response = '''
In JavaScript, you can reverse an array like this:
const reversed = arr.reverse();
'''

# Detection: check that output contains the correct language keyword
def check_language(response, expected_lang='def '):
    if expected_lang not in response:
        print(f'OFF-TOPIC FAILURE: expected {expected_lang} in response')
        return False
    return True

check_language(response)  # False — no Python def

# Hallucination detection via external verification
import requests

def verify_doi(doi):
    url = f'https://doi.org/{doi}'
    resp = requests.head(url, allow_redirects=True, timeout=5)
    return resp.status_code == 200

# Model claimed this paper exists:
fabricated_doi = '10.1234/fake.paper.2023.99999'
if not verify_doi(fabricated_doi):
    print('HALLUCINATION DETECTED: DOI does not exist')

import json
from datetime import datetime

def log_failure(prompt, response, failure_type, details=''):
    entry = {
        'timestamp': datetime.utcnow().isoformat(),
        'failure_type': failure_type,  # wrong_answer | wrong_format | off_topic | hallucination
        'prompt_hash': hash(prompt),
        'response_snippet': response[:200],
        'details': details
    }
    with open('prompt_failures.jsonl', 'a') as f:
        f.write(json.dumps(entry) + '\n')

log_failure(
    prompt=my_prompt,
    response=bad_response,
    failure_type='wrong_format',
    details='JSON prefix text broke parsing'
)

def classify_failure(prompt, expected, actual):
    classification_prompt = (
        f'You are a QA evaluator for LLM outputs.\n'
        f'Prompt: {prompt}\n'
        f'Expected behavior: {expected}\n'
        f'Actual output: {actual}\n\n'
        'Classify the failure as one of: CORRECT, WRONG_ANSWER, WRONG_FORMAT, OFF_TOPIC, HALLUCINATION.\n'
        'Reply with only the label.'
    )
    resp = client.chat.completions.create(
        model='gpt-4o-mini',
        messages=[{'role': 'user', 'content': classification_prompt}]
    )
    return resp.choices[0].message.content.strip()

import json
from collections import Counter

def failure_report(log_path='prompt_failures.jsonl'):
    entries = []
    with open(log_path) as f:
        for line in f:
            entries.append(json.loads(line))

    counts = Counter(e['failure_type'] for e in entries)
    total = len(entries)

    print(f'Total failures: {total}')
    for ftype, count in counts.most_common():
        pct = 100 * count / total
        print(f'  {ftype}: {count} ({pct:.1f}%)')

failure_report()