learn.ifs.name

ReAct: Synergizing Reasoning and Acting in Language Models

Yao et al., 2023, ReAct (The Eleventh International Conference on Learning Representations (ICLR 2023))

Subscriber deck — free during early access

1 cards in “3.1 Setup” · whole deck

3.1 Setup

  1. What action space did ReAct use for HotpotQA and FEVER?
    A deliberately simple Wikipedia API: search[entity] (first five sentences of the page, or five similar titles), lookup[string] (next sentence containing the string, like Ctrl+F) and finish[answer]. It is far weaker than real retrievers, forcing retrieval to be driven by explicit reasoning.
    • Yao et al., 2023, ReAct (The Eleventh International Conference on Learning Representations (ICLR 2023)), §3.1

Source

  • Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik Narasimhan and Yuan Cao. 2023. ReAct: Synergizing Reasoning and Acting in Language Models. In The Eleventh International Conference on Learning Representations (ICLR 2023). https://arxiv.org/abs/2210.03629