日期: 2023 年 12 月 25 日

Turbulence: Systematically and Automatically Testing Instruction-Tuned Large Language Models for Code[URL]Authors: Shahin Honarvar ; Mark van der Wilk ; Alastair DonaldsonTurbulence: Systematically and Automatically Testing Instruction-Tuned Large Language Models for Code[URL]Authors: Shahin Honarvar ; Mark van der Wilk ; Alastair Donaldson

2023-12-252023-12-25| C3P00Turbulence: Systematically and Automatically Testing Instruction-Tuned Large Language Models for Code[URL]Authors: Shahin Honarvar ; Mark van der Wilk ; Alastair Donaldson| 0 Comment| 21:22

Summary: We present a method for systematically evaluat […] [...]

View MoreView More

NPHardEval: Dynamic Benchmark on Reasoning Ability of Large Language Models via Complexity ClassesNPHardEval: Dynamic Benchmark on Reasoning Ability of Large Language Models via Complexity Classes

2023-12-252023-12-25| C3P00NPHardEval: Dynamic Benchmark on Reasoning Ability of Large Language Models via Complexity Classes| 0 Comment| 21:06

Q: 这篇论文试图解决什么问题？ A: 这篇论文旨在解决大型语言模型（LLMs）在推理能力评估方面的局限性。现 […] [...]

View MoreView More