cpldcpu/MisguidedAttention

A collection of prompts to challenge the reasoning abilities of large language models in presence of misguiding information

2 best points · 0 comments · 1 Hacker News post · 489 GitHub stars · View on GitHub

Hacker News discussions

• Misguided Attention – Prompts to challenge the reasoning ability of LLMs (2 points, 0 comments, by cpldcpu, 2024-11-10)