gen-ai
/
Prompt-Engineering-Guide
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Merge pull request #147 from Wind2esg/patch-1 

Update react.en.mdx
pull/155/head
Elvis Saravia 2023-04-25 09:11:00 -06:00 committed by GitHub
parent 5b059f20ee 973f831181
commit 3c929b01b8
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
pages/techniques/react.en.mdx
View File

@ -89,7 +89,7 @@ We can also observe that ReAct outperforms CoT on Fever and lags behind CoT on H
Prompting methods that combine and support switching between ReAct and CoT+Self-Consistency generally outperform all the other prompting methods. Prompting methods that combine and support switching between ReAct and CoT+Self-Consistency generally outperform all the other prompting methods.
## Results on Knowledge-Intensive Tasks ## Results on Decision Making Tasks
The paper also reports results demonstrating ReAct's performance on decision making tasks. ReAct is evaluated on two benchmarks called [ALFWorld](https://alfworld.github.io/) (text-based game) and [WebShop](https://webshop-pnlp.github.io/) (online shopping website environment). Both involve complex environments that require reasoning to act and explore effectively. The paper also reports results demonstrating ReAct's performance on decision making tasks. ReAct is evaluated on two benchmarks called [ALFWorld](https://alfworld.github.io/) (text-based game) and [WebShop](https://webshop-pnlp.github.io/) (online shopping website environment). Both involve complex environments that require reasoning to act and explore effectively.