Tree of Thoughts: Deliberate Problem Solving with Large Language Models
Yao et al., 2023, Tree of Thoughts (Advances in Neural Information Processing Systems 36 (NeurIPS 2023))
Subscriber deck — free during early access
1 cards in “4.2 Creative writing” · whole deck
4.2 Creative writing
- How was Tree of Thoughts applied to creative writing, and with what result?Task: write four paragraphs ending in four given random sentences. ToT generated 5 plans, let the model vote on the best, then wrote 5 passages from it and voted again. GPT-4 rated coherence 7.56 vs 6.93 for CoT and 6.19 for IO; humans preferred ToT over CoT 41 times to 21 out of 100.
- Yao et al., 2023, Tree of Thoughts (Advances in Neural Information Processing Systems 36 (NeurIPS 2023)), §4.2
Source
- Shunyu Yao, Dian Yu, Jeffrey Zhao, Izhak Shafran, Thomas L. Griffiths, Yuan Cao and Karthik Narasimhan. 2023. Tree of Thoughts: Deliberate Problem Solving with Large Language Models. In Advances in Neural Information Processing Systems 36 (NeurIPS 2023). https://papers.nips.cc/paper_files/paper/2023/hash/271db9922b8d1f4dd7aaef84ed5ac703-Abstract-Conference.html