返回实验室

web / Decisions & routing

LLM 判决与特征提取对比

AI-assisted summaries and translations. Check original sources for context and performance claims.

blog · 原文语言: English

该实验在三项分类任务中对比了单次 Jev 调用判决与多维特征提取的效果。结果显示,尽管多维分解提升了日语 NLI 的性能,但同时也导致将良性内容误判为攻击的比例大幅增加。

译文摘要 · AI-assisted; check the original.

查看原文
JEVLAB decorative pixel illustration; not source mediaJEVLAB ART

Source notes

This is a linked resource, not an independent verification of performance, cost or results. Check the original for current details.

Collected
2026-09-21
Discovered via
awesomejev.com

Related source links

前十名

Supporter

  1. Wallpets
  2. Walltank
  3. Chowder
  4. Falconer
  5. Lemonpod
  6. Menta
  7. Sway
  8. Peon-Ping
  9. Zeron
  10. Guideless
Supporters