madaan/self-refine
LLMs can generate feedback on their work, use it to improve the output, and repeat this process iteratively.
PythonApache-2.0
Stargazers
- akh1r0ckTechno.send
- BinaryBrainLlamaIndex (@run-llama)
- bschleter
- cat-stack-boopSydney
- ChaoYue0307Nanyang Tech. Univ.
- danielz02Massachusetts Institute of Technology
- dmarxStability.ai, Eleuther.ai
- flrngel@Ainbr
- Geeks-SidIndiana University
- gkoren2
- henrypooleLos Angeles
- iAmIlluminatiChennai
- ismail-codarAnkara, Turkiye
- JeffCarpenterCanada
- Ki6an
- Kunlun-ZhuMila-Quebec AI Institute; UdeM
- LangDaoAI
- leesky1cShanghai AI Lab
- liuyukid
- martyn255LABS
- mauryalandParis
- meet-cjli
- MrQ-Code
- nagpuri
- nigelleejyl
- pavelklymenkoSan Francisco Bay Area
- pyoner
- qianthinkingALO7
- rodrigobaronBrazil
- ShaoTengLiuCUHK
- shyamsn97
- sk413025Academia Sinica
- SpshulemSan Francisco
- tosi-nUnited Kingdom
- unverciftciMath & AI Institute
- vturrisiUniversity of Trento