Merge pull request #411 from matteofigus/patch-1

Update react.en.mdx

pages/techniques/react.en.mdx

@@ -19,7 +19,7 @@ Results show that ReAct can outperform several state-of-the-art baselines on lan
 
 ReAct is inspired by the synergies between "acting" and "reasoning" which allow humans to learn new tasks and make decisions or reasoning. 
 
-Chain-of-thought (CoT) prompting has shown the capabilities of LLMs to carry out reasoning traces to generate answers to questions involving arithmetic and commonsense reasoning, among other tasks [(Wei et al., 2022)](https://arxiv.org/abs/2201.11903). But it's lack of access to the external world or inability to update its knowledge can lead to issues like fact hallucination and error propagation. 
+Chain-of-thought (CoT) prompting has shown the capabilities of LLMs to carry out reasoning traces to generate answers to questions involving arithmetic and commonsense reasoning, among other tasks [(Wei et al., 2022)](https://arxiv.org/abs/2201.11903). But its lack of access to the external world or inability to update its knowledge can lead to issues like fact hallucination and error propagation. 
 
 ReAct is a general paradigm that combines reasoning and acting with LLMs. ReAct prompts LLMs to generate verbal reasoning traces and actions for a task. This allows the system to perform dynamic reasoning to create, maintain, and adjust plans for acting while also enabling interaction to external environments (e.g., Wikipedia) to incorporate additional information into the reasoning. The figure below shows an example of ReAct and the different steps involved to perform question answering.