BIG-Bench

مجموعة معايير واسعة النطاق تضم أكثر من 200 مهمة جُمعت بشكل تعاوني لتقييم النماذج اللغوية الكبيرة، تشمل مهام حسابية ولغوية ومنطقية متنوعة.

A large-scale crowd-sourced benchmark suite of over 200 tasks for evaluating large language models, including arithmetic, linguistic, and logical reasoning tasks.

Also translated asمعيار BIG-Bench، مجموعة BIG-Bench

First appears in this corpus in: Emergent Abilities of Large Language Models (2022)

Appears in these papers

Emergent Abilities of Large Language Models2022 in the sky ✦
Are Emergent Abilities of Large Language Models a Mirage?2023 in the sky ✦
PaLM: Scaling Language Modeling with Pathways2022 in the sky ✦