Lifeboat Foundation

Interpretable language modeling via induction-head ngram models.

Eunji Kim, Sriya Mantena, Weiwei Yang, Chandan Singh, Sungroh Yoon, Jianfeng Gao Microsoft Research 2024 https://arxiv.org/abs/2411.

Large language models (LLMs) have made impressive…

Official code for ‘Interpretable Language Modeling via Induction-head Ngram Models’ — ejkim47/induction-gram.