Differentiable Subset Pruning of Transformer Heads
Li, Jiaoda, Cotterell, Ryan, Sachan, Mrinmaya
Published in Transactions of the Association for Computational Linguistics (17.12.2021)
Published in Transactions of the Association for Computational Linguistics (17.12.2021)
Get full text
Journal Article
Towards a Mechanistic Interpretation of Multi-Step Reasoning Capabilities of Language Models
Hou, Yifan, Li, Jiaoda, Fei, Yu, Stolfo, Alessandro, Zhou, Wangchunshu, Zeng, Guangtao, Bosselut, Antoine, Sachan, Mrinmaya
Year of Publication 22.10.2023
Year of Publication 22.10.2023
Get full text
Journal Article
A Transformer with Stack Attention
Li, Jiaoda, White, Jennifer C, Sachan, Mrinmaya, Cotterell, Ryan
Published in arXiv.org (13.05.2024)
Get full text
Published in arXiv.org (13.05.2024)
Paper