Announcing our new Course: AI Red-Teaming and AI Safety Masterclass
Check it out →ReAct (Reason + Act)1 is a paradigm that enables Large Language Models (LLMs) to solve complex tasks through natural language reasoning and actions. It allows an LLM to perform certain actions, such as retrieving external information, and then reason based on the retrieved data.
ReAct systems extend Modular Reasoning, Knowledge, and Language (MRKL) systems by adding the ability to reason about the actions they can perform.
Below is an example from HotPotQA2, a question-answering dataset requiring complex reasoning. ReAct allows the LLM to reason about the question (Thought 1), take actions (e.g., querying Google) (Act 1). It then receives an observation (Obs 1) and continues the thought-action loop until reaching a conclusion (Act 3).
Readers with knowledge of Reinforcement Learning (RL) may recognize this process as similar to the classic RL loop of state, action and reward. ReAct provides some formalization for this in their paper.
Google experimented with the PaLM LLM3 using ReAct, and the results showed promising improvements in complex reasoning tasks. ReAct was tested on datasets such as FEVER4, focusing on fact extraction and verification.
Yao, S., Zhao, J., Yu, D., Du, N., Shafran, I., Narasimhan, K., & Cao, Y. (2022). ↩
Yang, Z., Qi, P., Zhang, S., Bengio, Y., Cohen, W. W., Salakhutdinov, R., & Manning, C. D. (2018). HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering. ↩
Chowdhery, A., Narang, S., Devlin, J., Bosma, M., Mishra, G., Roberts, A., Barham, P., Chung, H. W., Sutton, C., Gehrmann, S., Schuh, P., Shi, K., Tsvyashchenko, S., Maynez, J., Rao, A., Barnes, P., Tay, Y., Shazeer, N., Prabhakaran, V., … Fiedel, N. (2022). PaLM: Scaling Language Modeling with Pathways. ↩
Thorne, J., Vlachos, A., Christodoulopoulos, C., & Mittal, A. (2018). FEVER: a large-scale dataset for Fact Extraction and VERification. ↩