DLeX: AI Python

✔️ LLMs can't self-correct in reasoning tasks, DeepMind Study finds
استادی جدید دیپ‌مایند درباره ناتوانی اصلاح مدل‌های زبانی در تسک‌هایی که نیاز به استدلال دارن.

🔗 https://bdtechtalks.com/2023/10/09/llm-self-correction-reasoning-failures/

#LLMs #DeepMind

@ai_python

TechTalks

LLMs can’t self-correct in reasoning tasks, DeepMind study finds

A study by Google's DeepMind and the University of Illinois at Urbana-Champaign has found that self-correction in large language models (LLMs) isn't universally effective.

www.tgoop.com/ai_python/16181

4.1K viewsAmir, Oct 10, 2023 at 12:05

✔️ LLMs can't self-correct in reasoning tasks, DeepMind Study finds
استادی جدید دیپ‌مایند درباره ناتوانی اصلاح مدل‌های زبانی در تسک‌هایی که نیاز به استدلال دارن.

🔗 https://bdtechtalks.com/2023/10/09/llm-self-correction-reasoning-failures/

#LLMs #DeepMind

@ai_python

BY DLeX: AI Python