结构化文本解析中的正则表达式 vs LLM¶

テキスト形式は一貫していて繰り返しがあるか？
├── はい (>90% が何らかのパターンに従う) → 正規表現から始める
│   ├── 正規表現が 95%+ を処理 → 完了、LLM は不要
│   └── 正規表現が <95% を処理 → エッジケースのみ LLM を追加
└── いいえ (自由形式、高度に可変) → LLM を直接使用

[正規表現パーサー] ─── 構造を抽出（95〜98% の精度）
    │
    ▼
[テキストクリーナー] ─── ノイズを除去（マーカー、ページ番号、アーティファクト）
    │
    ▼
[信頼度スコアラー] ─── 信頼度の低い抽出結果にフラグを立てる
    │
    ├── 高信頼度（≥0.95）→ 直接出力
    │
    └── 低信頼度（<0.95）→ [LLM バリデーター] → 出力

import re
from dataclasses import dataclass

@dataclass(frozen=True)
class ParsedItem:
    id: str
    text: str
    choices: tuple[str, ...]
    answer: str
    confidence: float = 1.0

def parse_structured_text(content: str) -> list[ParsedItem]:
    """Parse structured text using regex patterns."""
    pattern = re.compile(
        r"(?P<id>\d+)\.\s*(?P<text>.+?)\n"
        r"(?P<choices>(?:[A-D]\..+?\n)+)"
        r"Answer:\s*(?P<answer>[A-D])",
        re.MULTILINE | re.DOTALL,
    )
    items = []
    for match in pattern.finditer(content):
        choices = tuple(
            c.strip() for c in re.findall(r"[A-D]\.\s*(.+)", match.group("choices"))
        )
        items.append(ParsedItem(
            id=match.group("id"),
            text=match.group("text").strip(),
            choices=choices,
            answer=match.group("answer"),
        ))
    return items

@dataclass(frozen=True)
class ConfidenceFlag:
    item_id: str
    score: float
    reasons: tuple[str, ...]

def score_confidence(item: ParsedItem) -> ConfidenceFlag:
    """Score extraction confidence and flag issues."""
    reasons = []
    score = 1.0

    if len(item.choices) < 3:
        reasons.append("few_choices")
        score -= 0.3

    if not item.answer:
        reasons.append("missing_answer")
        score -= 0.5

    if len(item.text) < 10:
        reasons.append("short_text")
        score -= 0.2

    return ConfidenceFlag(
        item_id=item.id,
        score=max(0.0, score),
        reasons=tuple(reasons),
    )

def identify_low_confidence(
    items: list[ParsedItem],
    threshold: float = 0.95,
) -> list[ConfidenceFlag]:
    """Return items below confidence threshold."""
    flags = [score_confidence(item) for item in items]
    return [f for f in flags if f.score < threshold]

def validate_with_llm(
    item: ParsedItem,
    original_text: str,
    client,
) -> ParsedItem:
    """Use LLM to fix low-confidence extractions."""
    response = client.messages.create(
        model="claude-haiku-4-5-20251001",  # Cheapest model for validation
        max_tokens=500,
        messages=[{
            "role": "user",
            "content": (
                f"Extract the question, choices, and answer from this text.\n\n"
                f"Text: {original_text}\n\n"
                f"Current extraction: {item}\n\n"
                f"Return corrected JSON if needed, or 'CORRECT' if accurate."
            ),
        }],
    )
    # Parse LLM response and return corrected item...
    return corrected_item

def process_document(
    content: str,
    *,
    llm_client=None,
    confidence_threshold: float = 0.95,
) -> list[ParsedItem]:
    """Full pipeline: regex -> confidence check -> LLM for edge cases."""
    # Step 1: Regex extraction (handles 95-98%)
    items = parse_structured_text(content)

    # Step 2: Confidence scoring
    low_confidence = identify_low_confidence(items, confidence_threshold)

    if not low_confidence or llm_client is None:
        return items

    # Step 3: LLM validation (only for flagged items)
    low_conf_ids = {f.item_id for f in low_confidence}
    result = []
    for item in items:
        if item.id in low_conf_ids:
            result.append(validate_with_llm(item, content, llm_client))
        else:
            result.append(item)

    return result