✔️ 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
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.