Do not think that much for 2+3=? 论文粗读
Do not think that much for 2+3=? 论文粗读
💡 Meta Data
Title | Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs |
---|---|
Journal | (10.48550/arXiv.2412.21187) |
Authors | Chen Xingyu,Xu Jiahao,Liang Tian,He Zhiwei,Pang Jianhui,Yu Dian,Song Linfeng,Liu Qiuzhi,Zhou Mengfei,Zhang Zhuosheng,Wang Rui,Tu Zhaopeng,Mi Haitao,Yu Dong |
Pub.date | 2024-12-30 |
To CoT or not to CoT? 论文粗读
To CoT or not to CoT? 论文粗读
💡 Meta Data
Title | To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning |
---|---|
Journal | (10.48550/arXiv.2409.12183) |
Authors | Sprague Zayne,Yin Fangcong,Rodriguez Juan Diego,Jiang Dongwei,Wadhwa Manya,Singhal Prasann,Zhao Xinyu,Ye Xi,Mahowald Kyle,Durrett Greg |
Pub.date | 2024-10-29 |
AnyTool-论文粗读
AnyTool 论文粗读
💡 Meta Data
Title | AnyTool: Self-Reflective, Hierarchical Agents for Large-Scale API Calls |
---|---|
Journal | (10.48550/arXiv.2402.04253 ICML 2024) |
Authors | Du Yu,Wei Fangyun,Zhang Hongyang |
Pub.date | 2024-02-06 |
Towards-Autonomous-Tool-Utilization-论文粗读
Towards Autonomous Tool Utilization论文粗读
💡 Meta Data
Title | Towards Autonomous Tool Utilization in Language Models: A Unified, Efficient and Scalable Framework |
---|---|
Journal | (LREC-COLING) |
Authors | Li Zhi,Li Yicheng,Ye Hequan,Zhang Yin |
Pub.date |
Why Can GPT ICL 论文粗读
Why Can GPT ICL 论文粗读
💡 Meta Data
Title | Why Can GPT Learn In-Context? Language Models Implicitly Perform Gradient Descent as Meta-Optimizers |
---|---|
Journal | (acl 2023) |
Authors | Dai Damai,Sun Yutao,Dong Li,Hao Yaru,Ma Shuming,Sui Zhifang,Wei Furu |
Pub.date |
TooL LLM 论文粗读
<TooL LLM> 论文粗读
💡 Meta Data
Title | ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs |
---|---|
Journal | (10.48550/arXiv.2307.16789) |
Authors | Qin Yujia,Liang Shihao,Ye Yining,Zhu Kunlun,Yan Lan,Lu Yaxi,Lin Yankai,Cong Xin,Tang Xiangru,Qian Bill,Zhao Sihan,Hong Lauren,Tian Runchu,Xie Ruobing,Zhou Jie,Gerstein Mark,Li Dahai,Liu Zhiyuan,Sun Maosong |
Pub.date | 2023-10-03 |
Toolformer 论文粗读
<Toolformer> 论文粗读
💡 Meta Data
Title | Toolformer: Language Models Can Teach Themselves to Use Tools |
---|---|
Journal | (10.48550/ARXIV.2302.04761) |
Authors | Schick Timo,Dwivedi-Yu Jane,Dessì Roberto,Raileanu Roberta,Lomeli Maria,Zettlemoyer Luke,Cancedda Nicola,Scialom Thomas |
Pub.date | 2023 |
共计 84 篇文章,11 页。