Jump to content
Main menu
Main menu
move to sidebar
hide
Navigation
Main page
Current events
Recent changes
Random page
Help
Categories
LemonWiki共筆
Search
Search
Appearance
Log in
Personal tools
Log in
Pages for logged out editors
learn more
Contributions
Talk
Editing
Generative AI glossary
(section)
Page
Discussion
English
Read
Edit
View history
Tools
Tools
move to sidebar
hide
Actions
Read
Edit
View history
General
What links here
Related changes
Special pages
Page information
Appearance
move to sidebar
hide
Warning:
You are not logged in. Your IP address will be publicly visible if you make any edits. If you
log in
or
create an account
, your edits will be attributed to your username, along with other benefits.
Anti-spam check. Do
not
fill this in!
== S == * AI Sycophancy(AI 諂媚):「模型在預訓練階段即呈現出迎合使用者立場的傾向,而『基於人類回饋的強化學習』(Reinforcement Learning from Human Feedback, RLHF) 可能進一步放大此行為。由於偏好模型往往將『與使用者觀點一致』視為高品質回應,模型因此更可能選擇迎合而非糾正,即使使用者的立場並不正確。」(Sharma et al., 2025<ref>Sharma et al., "Towards Understanding Sycophancy in Language Models", Anthropic — https://arxiv.org/abs/2310.13548</ref><ref>[https://errerrors.blogspot.com/2026/01/google-ai-overviews-confirmation-bias.html Google AI 摘要的「迎合偏誤」問題:為什麼 AI 會說你想聽的話?]</ref>)
Summary:
Please note that all contributions to LemonWiki共筆 are considered to be released under the Creative Commons Attribution-NonCommercial-ShareAlike (see
LemonWiki共筆:Copyrights
for details). If you do not want your writing to be edited mercilessly and redistributed at will, then do not submit it here.
You are also promising us that you wrote this yourself, or copied it from a public domain or similar free resource.
Do not submit copyrighted work without permission!
Cancel
Editing help
(opens in new window)