Hey, can you please add me to this?
24.11.2024 06:23
π 2
π 0
π¬ 0
π 0
Please add
20.11.2024 23:08
π 2
π 0
π¬ 1
π 0
β
20.11.2024 22:53
π 0
π 0
π¬ 1
π 0
How do LLMs learn to reason from data? Are they ~retrieving the answers from parametric knowledgeπ¦? In our new preprint, we look at the pretraining data and find evidence against this:
Procedural knowledge in pretraining drives LLM reasoning βοΈπ’
π§΅β¬οΈ
20.11.2024 16:31
π 854
π 137
π¬ 36
π 24
Thanks Tim for sharing, I submitted my application.
19.11.2024 01:48
π 0
π 0
π¬ 0
π 0