[2402.12875] Chain of Thought Empowers Transformers to Solve Inherently Serial Problems

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. arXiv Operational Status Get status notifications via email or slack

[2402.12875] Chain of Thought Empowers Transformers to Solve Inherently Serial Problems --> Computer Science > Machine Learning arXiv:2402.12875 (cs) [Submitted on 20 Feb 2024 ( v1 ), last revised 21 Sep 2024 (this version, v4)] Title: Chain of Thought Empowers Transformers to Solve Inherently Serial Problems Authors: Zhiyuan Li , Hong Liu , Denny Zhou , Tengyu Ma View a PDF of the paper titled Chain of Thought Empowers Transformers to Solve Inherently Serial Problems, by Zhiyuan Li and 3 other authors View PDF HTML (experimental) Abstract: Instructing the model to generate a sequence of inter

saved by

• OIeg Viatkin

related reading

• 2402.12875arxiv.org
• Transformers Provably Learn to Internalize Chain-of-Thoughtarxiv.org
• A Mathematical Framework for Transformer Circuitstransformer-circuits.pub
• Let's Think Dot by Dot: Hidden Computation in Transformer Language Modelsarxiv.org
• [2404.15758] Let's Think Dot by Dot: Hidden Computation in Transformer Language Modelsarxiv.org
• Transformers Learn to Implement Multi-step Gradient Descent with Chain of Thoughtarxiv.org
• 2305.18654arxiv.org
• Quantifying the Necessity of Chain of Thought through Opaque Serial Deptharxiv.org
• 2404.15758arxiv.org
• 2305.18654.pdfarxiv.org
• Exact Expressive Power of Transformers with Paddingarxiv.org
• [2305.18654] Faith and Fate: Limits of Transformers on Compositionalityarxiv.org