신규 파일: - classifier_service.py: exaone binary classifier (sufficient/insufficient) parallel with evidence, circuit breaker, timeout 5s - refusal_gate.py: multi-signal fusion (score + classifier) AND 조건, conservative fallback 3-tier (classifier 부재 시) - grounding_check.py: strong/weak flag 분리 strong: fabricated_number + intent_misalignment(important keywords) weak: uncited_claim + low_overlap + intent_misalignment(generic) re-gate: 2+ strong → refuse, 1 strong → partial - sentence_splitter.py: regex 기반 (Phase 3.5b KSS 업그레이드) - classifier.txt: exaone Y+ prompt (calibration examples 포함) - search_synthesis_partial.txt: partial answer 전용 프롬프트 - 102_ask_events.sql: /ask 관측 테이블 (completeness 3-분리 지표) - queries.yaml: Phase 3.5 smoke test 평가셋 10개 수정 파일: - search.py /ask: classifier parallel + refusal gate + grounding re-gate + defense_layers 로깅 + AskResponse completeness/aspects/confirmed_items - config.yaml: classifier model 섹션 (exaone3.5:7.8b GPU Ollama) - config.py: classifier optional 파싱 - AskAnswer.svelte: 4분기 렌더 (full/partial/insufficient/loading) - ask.ts: Completeness + ConfirmedItem 타입 P1 실측: exaone ternary 불안정 → binary gate 축소. partial은 grounding이 담당. 토론 9라운드 확정. plan: quiet-meandering-nova.md Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
35 lines
1011 B
Plaintext
35 lines
1011 B
Plaintext
You are a grounded answer synthesizer handling a PARTIAL answer case. Some aspects of the query CAN be answered, others CANNOT. Respond ONLY in JSON.
|
|
|
|
## Task
|
|
Answer ONLY the covered aspects. Do NOT attempt to answer missing aspects.
|
|
|
|
## Output Schema
|
|
{
|
|
"confirmed_items": [
|
|
{"aspect": "aspect label", "text": "1~2 sentence answer", "citations": [1, 2]}
|
|
],
|
|
"confidence": "medium" | "low",
|
|
"refused": false
|
|
}
|
|
|
|
## Rules
|
|
- Each confirmed_item: aspect label + 1~2 sentences + inline [n] citations
|
|
- ONLY use facts present in evidence. No outside knowledge, no guessing.
|
|
- Do NOT mention or address missing_aspects in your text.
|
|
- Korean query → Korean answer / English → English
|
|
- confidence: medium (2+ strong evidence matches) / low (1 or weak)
|
|
- Max total text: 400 chars across all items
|
|
- 모든 주장 문장 끝에 [n] 필수
|
|
|
|
## Covered aspects (answer these):
|
|
{covered_aspects}
|
|
|
|
## Missing aspects (do NOT answer these):
|
|
{missing_aspects}
|
|
|
|
## Query
|
|
{query}
|
|
|
|
## Evidence
|
|
{numbered_evidence}
|