Abstract

Gasper Begus: LLMs as linguists: Using linguistic formalism as a window into LLMs metacognitive abilities

Jia Xu: Infinite Reservoir Transformer

Fereshte Khani: collaborative development of NLP models

Weijie Su: Reward Collapse in Aligning Large Language Models

Song Mei: Transformers as Statisticians: Provable In-Context Learning with In-Context Algorithm Selection

Bob Carpenter: Soft RLHF training with probabilistic rating models