2402.12875

N/A

Chain of Thought Empowers Transformers to Solve Inherently Serial Problems Zhiyuan Li1,2 , Hong Liu1 , Denny Zhou3 , and Tengyu Ma1 1 Stanford University, 2 Toyota Technological Institute at Chicago, 3 Google arXiv:2402.12875v4 [cs.LG] 21 Sep 2024 Abstract…

saved by

• OIeg Viatkin

related reading

• [2402.12875] Chain of Thought Empowers Transformers to Solve Inherently Serial Problemsarxiv.org
• A Mathematical Framework for Transformer Circuitstransformer-circuits.pub
• Circuit Tracing: Revealing Computational Graphs in Language Modelstransformer-circuits.pub
• [2201.11903] Chain of Thought Prompting Elicits Reasoning in Large Language Modelsarxiv.org
• [2404.15758] Let's Think Dot by Dot: Hidden Computation in Transformer Language Modelsarxiv.org
• 2305.18654arxiv.org
• [2412.06769] Training Large Language Models to Reason in a Continuous Latent Spacearxiv.org
• 2404.15758arxiv.org
• Transformers Provably Learn to Internalize Chain-of-Thoughtarxiv.org
• [2604.24737] Learning to Think from Multiple Thinkersarxiv.org
• 2305.18654.pdfarxiv.org
• Training Large Language Models to Reason in a Continuous Latent Spacearxiv.org