bluemsi/2nd
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

docs: finalized wiki integrity maintenance (v3.0 standard) - pruned 1400+ stubs and fixed 11k+ ghost links

Browse Source
This commit is contained in:
Antigravity Agent
2026-05-02 09:18:34 +09:00
parent c84dcb8371
commit 6445fcc05b
13150 changed files with 55394 additions and 100862 deletions
Download Patch File Download Diff File Expand all files Collapse all files
10_Wiki/Topics_GD/Best-of-N Sampling (최적 샘플링).md
+3 -3
View File
@@ -2,11 +2,11 @@
id: BON-001
category: "10_Wiki/💡 Topics/AI"
confidence_score: 1.0
tags: [ai-inference, llm, sampling-[[Strategy]], post-[[Processing]]]
tags: [ai-inference, llm, sampling-[[Strategy|Strategy]], post-[[Processing|Processing]]]
last_reinforced: 2026-04-26
---
# [[Best-of-N Sampling (최적 샘플링)]]
# [[Best-of-N Sampling (최적 샘플링)|Best-of-N Sampling (최적 샘플링)]]
## 📌 한 줄 통찰 (The Karpathy Summary)
> "많이 뽑고 가장 좋은 것을 골라라" — 모델로부터 N개의 응답을 생성한 뒤, 별도의 보상 모델(RM)이나 채점 기준을 통해 가장 품질이 높은 최적의 답변 하나를 선택하는 추론 최적화 기법.
@@ -26,4 +26,4 @@ last_reinforced: 2026-04-26
## 🔗 지식 연결 (Graph)
- **Parent:** 10_Wiki/💡 Topics/AI
- **Related:** Chain-of-Thought, Self-Consistency, Reward-Modeling
- **Raw Source:** 00_Raw/2026-04-20/[[Best-of-N Sampling]].md
- **Raw Source:** 00_Raw/2026-04-20/[[Best-of-N Sampling|Best-of-N Sampling]].md