- I reversed engineered how WizardMath actually works. The 3-step process is brilliant. [Technical Analysis] https://blog.bagel.net/p/train-fast-but-think-slow 3 comments deeplearning
- [R][D] Pattern Matching != Reasoning: We analyzed 2 distinct paths to make LLMs actually think [Technical Deep Dive] https://blog.bagel.net/p/train-fast-but-think-slow 7 comments machinelearning
- Pattern Matching != Reasoning: We analyzed 2 distinct paths to make LLMs actually think [Technical Deep Dive] https://blog.bagel.net/p/train-fast-but-think-slow 17 comments learnmachinelearning
Linked pages
- [2211.12588] Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks https://arxiv.org/abs/2211.12588 6 comments
- [2201.11903] Chain of Thought Prompting Elicits Reasoning in Large Language Models https://arxiv.org/abs/2201.11903 1 comment
- [2206.14858] Solving Quantitative Reasoning Problems with Language Models https://arxiv.org/abs/2206.14858 0 comments
- [2211.09085] Galactica: A Large Language Model for Science https://arxiv.org/abs/2211.09085 0 comments
- [2211.10435] PAL: Program-aided Language Models https://arxiv.org/abs/2211.10435 0 comments
- [2205.10625] Least-to-Most Prompting Enables Complex Reasoning in Large Language Models https://arxiv.org/abs/2205.10625 0 comments
- [2304.12244] WizardLM: Empowering Large Language Models to Follow Complex Instructions https://arxiv.org/abs/2304.12244 0 comments
Would you like to stay up to date with Computer science? Checkout Computer science
Weekly.
Related searches:
Search whole site: site:blog.bagel.net
Search title: Train Fast, But Think Slow
See how to search.