불확실성을 인지하는 LLM 시스템 구축하기: 신뢰도 추정, 자기 평가 및 자동 검색 파이프라인

SYSTEM_UNCERTAINTY = """
You are an expert AI assistant that is HONEST about what it knows and doesn't know.
For every question you MUST respond with valid JSON only (no markdown, no prose outside JSON):
{
 "answer": "",
 "confidence": ,
 "reasoning": ""
}
Confidence scale:
0.90-1.00 → very high: well-established fact, you are certain
0.75-0.89 → high: strong knowledge, minor uncertainty
0.55-0.74 → medium: plausible but you may be wrong, could be outdated
0.30-0.54 → low: significant uncertainty, answer is a best guess
0.00-0.29 → very low: mostly guessing, minimal reliable knowledge
""".strip()

def self_evaluate(response: LLMResponse) -> LLMResponse:
    critique_prompt = f"""
    Review this answer and its stated confidence. Check for:
    1. Logical consistency
    2. Whether the confidence matches the actual quality of the answer
    3. Any factual errors you can spot
    Question: {response.question}
    Proposed answer: {response.answer}
    Stated confidence: {response.confidence}
    Stated reasoning: {response.reasoning}
    Respond in JSON: {{ "revised_confidence": , "critique": "", "revised_answer": "" }}
    """.strip()
    // ...(중략)
    ev = json.loads(completion.choices[0].message.content)
    response.confidence = float(ev.get("revised_confidence", response.confidence))
    response.answer = ev.get("revised_answer", response.answer)
    return response

def research_and_synthesize(response: LLMResponse) -> LLMResponse:
    console.print(f" [yellow]🔍 Confidence {response.confidence:.0%} is low — triggering auto-research...[/yellow]")
    snippets = web_search(response.question)
    if not snippets:
        return response
    
    synthesis_prompt = f"""
    Question: {response.question}
    Preliminary answer (low confidence): {response.answer}
    Web search snippets: {formatted}
    Synthesize an improved answer using the evidence above.
    """.strip()
    // ...(중략)
    syn = json.loads(completion.choices[0].message.content)
    response.answer = syn.get("answer", response.answer)
    response.confidence = float(syn.get("confidence", response.confidence))
    return response