# I am the Watcher. I am your guide through this vast new twtiverse.
# 
# Usage:
#     https://watcher.sour.is/api/plain/users              View list of users and latest twt date.
#     https://watcher.sour.is/api/plain/twt                View all twts.
#     https://watcher.sour.is/api/plain/mentions?uri=:uri  View all mentions for uri.
#     https://watcher.sour.is/api/plain/conv/:hash         View all twts for a conversation subject.
# 
# Options:
#     uri     Filter to show a specific users twts.
#     offset  Start index for quey.
#     limit   Count of items to return (going back in time).
# 
# twt range = 1 1
# self = https://watcher.sour.is/conv/ncusv5a
yue-fang-readfog
feeds.twtxt.net
View Thread
大語言模型中的提示隱私保護**
一、簡介：-----大語言模型（LLM） 擁有龐大的規模、預先訓練的知識和卓越的性能，被廣泛應用於各種任務。提示學習 (prompt learning) 和指令微調(instruction tuning) 是兩種重要的使得大模型能理解具體任務的技術手段。然而，這些 prompt 或 instruction 常常會包含隱私信息，使得難以直接共享。本文講解了兩篇大語言模型中的 prompt 和 ins ⌘ Read more