mrconter1/LongScope

LongScope is a benchmark for assessing large language models' ability to handle fragmented knowledge in extended textual contexts.

1 best points · 4 comments · 1 Hacker News post · 5 GitHub stars · View on GitHub

Hacker News discussions

• LongScope: Assessing fragmented knowledge use in extended contexts (1 points, 4 comments, by AIReach, 2023-12-07)