Timezone: »

Confident Adaptive Language Modeling
Tal Schuster · Adam Fisch · Jai Gupta · Mostafa Dehghani · Dara Bahri · Vinh Tran · Yi Tay · Donald Metzler

Wed Nov 30 09:00 AM -- 11:00 AM (PST) @ Hall J #640
Recent advances in Transformer-based large language models (LLMs) have led to significant performance improvements across many tasks. These gains come with a drastic increase in the models' size, potentially leading to slow and costly use at inference time. In practice, however, the series of generations made by LLMs is composed of varying levels of difficulty. While certain predictions truly benefit from the models' full capacity, other continuations are more trivial and can be solved with reduced compute. In this work, we introduce Confident Adaptive Language Modeling (CALM), a framework for dynamically allocating different amounts of compute per input and generation timestep. Early exit decoding involves several challenges that we address here, such as: (1) what confidence measure to use; (2) connecting sequence-level constraints to local per-token exit decisions; and (3) attending back to missing hidden representations due to early exits in previous tokens. Through theoretical analysis and empirical experiments on three diverse text generation tasks, we demonstrate the efficacy of our framework in reducing compute---potential speedup of up to $\times 3$---while provably maintaining high performance.

Author Information

Tal Schuster (Google Research)
Adam Fisch (Massachusetts Institute of Technology)
Jai Gupta (Indian Institute of Technology Kharagpur)
Mostafa Dehghani (Google Brain)
Dara Bahri (Google AI)
Vinh Tran (Google)
Yi Tay (Google Brain)
Donald Metzler (Google)

More from the Same Authors