March 13, 2024, 4:43 a.m. | Huaixiu Steven Zheng, Swaroop Mishra, Xinyun Chen, Heng-Tze Cheng, Ed H. Chi, Quoc V Le, Denny Zhou

cs.LG updates on arXiv.org arxiv.org

arXiv:2310.06117v2 Announce Type: replace
Abstract: We present Step-Back Prompting, a simple prompting technique that enables LLMs to do abstractions to derive high-level concepts and first principles from instances containing specific details. Using the concepts and principles to guide reasoning, LLMs significantly improve their abilities in following a correct reasoning path towards the solution. We conduct experiments of Step-Back Prompting with PaLM-2L, GPT-4 and Llama2-70B models, and observe substantial performance gains on various challenging reasoning-intensive tasks including STEM, Knowledge QA, and …

abstract abstraction abstractions arxiv concepts cs.ai cs.cl cs.lg guide instances language language models large language large language models llms prompting reasoning simple type via

Senior Data Engineer

@ Displate | Warsaw

Werkstudent Product Data Management (m/w/d)

@ ABOUT YOU SE & Co. KG | Hamburg, Germany

Data Scientist

@ Meta | Sunnyvale, CA

Data Scientist, Analytics

@ Meta | Menlo Park, CA

Principal AI Engineer

@ Blankfactor | Romania - Bucharest

Data Engineer

@ DigiOutsource | Cape Town - Waterview Park