feat(ai): 종합 피드백 점수 산정을 하이브리드로 (앵커 루브릭 + per-answer 집계 기준값)#75
Merged
Conversation
기존엔 최종 0~100 점수를 LLM 이 자유 판정 → 재현성·기준 약함. per-answer 평가(specificity/logic/structure/correctness, 0~5)를 코드에서 차원별 0~100 기준값으로 결정론적 집계해 LLM 에 제시하고, ±15점 이내로 산정하도록 제약(하이브리드). 앵커 루브릭도 추가해 60 vs 80 의 의미를 캘리브레이션. - prompts/feedback_generation: 0~100 앵커 루브릭 + score_basis 슬롯 + "기준값 ±15 이내" 제약. correctness 근거 없으면 과대평가 금지. - feedback_consumer._build_score_basis: per-answer 평가 평균을 technical_accuracy(=correctness*20)/logic/communication(=specificity+structure) /overall 로 매핑. correctness 전무(참고문서 미선택)면 '근거 없음' 표기. - feedback chain/generator: score_basis 파라미터 전달. - 테스트 4종 추가, 전체 218 통과. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
기존엔 최종 0
100 점수를 LLM 이 자유 판정 → 재현성·기준 약함.5)를 코드에서 차원별 0~100 기준값으로 결정론적 집계해 LLM 에 제시하고,per-answer 평가(specificity/logic/structure/correctness, 0
±15점 이내로 산정하도록 제약(하이브리드). 앵커 루브릭도 추가해
60 vs 80 의 의미를 캘리브레이션.
변경 사항