KM Wiki

Home

โฏ

wiki

โฏ

Agents

โฏ

Frameworks

โฏ

Evaluations

โฏ

000_Evaluations-MOC

000_Evaluations-MOC

2026๋…„ 11์›” 17์ผ1 min read

Evaluations MOC

๐Ÿ“„ Documents

  • wiki/Agents/Frameworks/Evaluations/AI ์—์ด์ „ํŠธ Eval ์‹ฌ์ธต ๋ถ„์„.md
  • wiki/Agents/Frameworks/Evaluations/Agent-as-a-judge-Framework-์—์ด์ „ํŠธ-๊ธฐ๋ฐ˜-ํ‰๊ฐ€-ํ”„๋ ˆ์ž„์›Œํฌ.md

๊ทธ๋ž˜ํ”„ ๋ทฐ

  • Evaluations MOC
  • ๐Ÿ“„ Documents

๋ฐฑ๋งํฌ

  • 000_Agents-MOC
  • ABI ์‹ ๋ขฐ ํ”„๋ ˆ์ž„์›Œํฌ: AI ์ •์น˜์ธ ๋ฐ ์ •์น˜ ์‹œ์Šคํ…œ ํ‰๊ฐ€ ํ‘œ์ค€
  • AI ์—์ด์ „ํŠธ ํ‰๊ฐ€ ๋ฐฉ๋ฒ•๋ก  ๋ฐ ๋„๊ตฌ
  • AgentEval: ์ถ”๋ก  ๊ธฐ๋ฐ˜ ๋‹ค์ค‘ ์—์ด์ „ํŠธ ํ‰๊ฐ€ ํ”„๋ ˆ์ž„์›Œํฌ
  • Deep Agent ํ‰๊ฐ€ ํ”„๋ ˆ์ž„์›Œํฌ
  • Giskard OSS: LLM ์—์ด์ „ํŠธ ํ‰๊ฐ€ ๋ฐ ์ทจ์•ฝ์  ์Šค์บ” ํ”„๋ ˆ์ž„์›Œํฌ
  • HaluMem: ์—์ด์ „ํŠธ ๋ฉ”๋ชจ๋ฆฌ ์‹œ์Šคํ…œ์˜ ์ˆ˜์ง‘ยท์—…๋ฐ์ดํŠธยท์งˆ์˜(Extraction-Update-QA) ํ™˜๊ฐ ๊ฒ€์ฆ ๋ฒค์น˜๋งˆํฌ
  • JevAdvBench ๋ฐ ๊ฒฐ์ •ยท์ž๊ฐ€๊ฐœ์„  ๋ชจ๋ธ ํ‰๊ฐ€ ๊ฐ์‚ฌ: RLCD ์ ๋Œ€์  ๊ณต๊ฒฉ, LettuceDetect, RSI ๋ฒค์น˜๋งˆํฌ ํ•จ์ •
  • Judge ๋ชจ๋ธ ๋น„๊ต: LLM vs Agent as a Judge
  • TasteVal: AI ์—ฐ๊ตฌ ์ง๊ด€(Research Taste) ๋ฐ ๊ณผํ•™์  ํƒ๊ตฌ๋ ฅ ์ธก์ • ๋ฒค์น˜๋งˆํฌ
  • 000_Frameworks-MOC
  • 000_LLM-Agent-MOC
  • 000_T2SQL-MOC (Text-to-SQL Map of Content)
  • T2SQL ๋ฒค์น˜๋งˆํฌ 2026: ์—”ํ„ฐํ”„๋ผ์ด์ฆˆ ๋ฐ์ดํ„ฐ ๋ถ„์„ ์„ฑ๋Šฅ ํ‰๊ฐ€ ํ‘œ์ค€
  • Transformers.js