Skip to content
conftrace_

token dependency

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

early exit technique (1) layer permutation (1) contextualization error (1) inference intervention (1) large language model (1) non-autoregressive generation (1) pre-trained language model (1) inference efficiency (1) mechanistic interpretability (1) early exit (1)

Papers

Racing Thoughts: Explaining Contextualization Errors in Large Language Models NAACL 2025 ELMER: A Non-Autoregressive Pre-trained Language Model for Efficient and Effective Text Generation EMNLP 2022