| 标题 |
Prompt Repetition Improves Non-Reasoning LLMs
|
| 网址 |
求助人暂未提供
|
| DOI |
暂未提供，该求助的时间将会延长，查看原因？
|
| 其它 |
Yaniv Leviathan, Matan Kalman, Yossi Matias When not using reasoning, repeating the input prompt improves performance for popular models (Gemini, GPT, Claude, and Deepseek) without increasing the number of generated tokens or latency. Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computation and Language (cs.CL |
| 求助人 | |
| 下载 |
PDF的下载单位、IP信息已删除
(2025-6-4)
无极微光
大力的灵雁
zzzz
贪玩的秋柔
AllRightReserved
HH
lizishu
畔畔
乐空思
wanci
学术文献互助
科研狗
GingerF
浮浮世世
Mic
dew
三四郎
湖工大保卫处
pcr163
昏睡的蟠桃
皖公网安备34019202002308
