Fast and Robust Early-Exiting Framework for Autoregressive Language Models with Synchronized Parallel Decoding

Sangmin Bae, Jongwoo Ko, Hwanjun Song, Se-Young Yun

Submission Type: Regular Long Paper

Submission Track: Efficient Methods for NLP

Submission Track 2: Machine Learning for NLP

Keywords: Efficient Decoding of Language Model, Early-Exiting Framework, Parallel Decoding, Adaptive Confidence Estimation

Abstract: To tackle the high inference latency exhibited by autoregressive language models, previous studies have proposed an early-exiting framework that allocates adaptive computation paths for each token based on the complexity of generating the subsequent token. However, we observed several shortcomings, including performance degradation caused by a state copying mechanism or numerous exit paths, and sensitivity to exit confidence thresholds. Consequently, we propose a Fast and Robust Early-Exiting (FREE) framework, which incorporates a shallow-deep module and a synchronized parallel decoding. Our framework enables faster inference by synchronizing the decoding process of the current token with previously stacked early-exited tokens. Furthermore, as parallel decoding allows us to observe predictions from both shallow and deep models, we present a novel adaptive threshold estimator that exploits a Beta mixture model to determine suitable confidence thresholds. We empirically demonstrated the superiority of our proposed framework on extensive generation tasks.

Submission Number: 4296