A Thorough Examination of Decoding Methods in the Era of LLMs

Chufan Shi, Haoran Yang, Deng Cai, Zhisong Zhang, Yifan Wang, Yujiu Yang, Wai Lam


Abstract
Decoding methods play an indispensable role in converting language models from next-token predictors into practical task solvers. Prior research on decoding methods, primarily focusing on task-specific models, may not extend to the current era of general-purpose large language models (LLMs). Moreover, the recent influx of decoding strategies has further complicated this landscape. This paper provides a comprehensive and multifaceted analysis of various decoding methods within the context of LLMs, evaluating their performance, robustness to hyperparameter changes, and decoding speeds across a wide range of tasks, models, and deployment environments. Our findings reveal that decoding method performance is notably task-dependent and influenced by factors such as alignment, model size, and quantization. Intriguingly, sensitivity analysis exposes that certain methods achieve superior performance at the cost of extensive hyperparameter tuning, highlighting the trade-off between attaining optimal results and the practicality of implementation in varying contexts.
Anthology ID:
2024.emnlp-main.489
Volume:
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
8601–8629
Language:
URL:
https://aclanthology.org/2024.emnlp-main.489
DOI:
Bibkey:
Cite (ACL):
Chufan Shi, Haoran Yang, Deng Cai, Zhisong Zhang, Yifan Wang, Yujiu Yang, and Wai Lam. 2024. A Thorough Examination of Decoding Methods in the Era of LLMs. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 8601–8629, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
A Thorough Examination of Decoding Methods in the Era of LLMs (Shi et al., EMNLP 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.emnlp-main.489.pdf
Software:
 2024.emnlp-main.489.software.zip