Decoding Decoded: Understanding Hyperparameter Effects in Open-Ended Text Generation

Esteban Garces Arias, Meimingwei Li, Christian Heumann, Matthias Assenmacher


Abstract
Decoding strategies for generative large language models (LLMs) are a critical but often underexplored aspect of text generation tasks. Guided by specific hyperparameters, these strategies aim to transform the raw probability distributions produced by language models into coherent, fluent text. In this study, we undertake a large-scale empirical assessment of a range of decoding methods, open-source LLMs, textual domains, and evaluation protocols to determine how hyperparameter choices shape the outputs. Our experiments include both factual (e.g., news) and creative (e.g., fiction) domains, and incorporate a broad suite of automatic evaluation metrics alongside human judgments. Through extensive sensitivity analyses, we distill practical recommendations for selecting and tuning hyperparameters, noting that optimal configurations vary across models and tasks. By synthesizing these insights, this study provides actionable guidance for refining decoding strategies, enabling researchers and practitioners to achieve higher-quality, more reliable, and context-appropriate text generation outcomes.
Anthology ID:
2025.coling-main.668
Volume:
Proceedings of the 31st International Conference on Computational Linguistics
Month:
January
Year:
2025
Address:
Abu Dhabi, UAE
Editors:
Owen Rambow, Leo Wanner, Marianna Apidianaki, Hend Al-Khalifa, Barbara Di Eugenio, Steven Schockaert
Venue:
COLING
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
9992–10020
Language:
URL:
https://aclanthology.org/2025.coling-main.668/
DOI:
Bibkey:
Cite (ACL):
Esteban Garces Arias, Meimingwei Li, Christian Heumann, and Matthias Assenmacher. 2025. Decoding Decoded: Understanding Hyperparameter Effects in Open-Ended Text Generation. In Proceedings of the 31st International Conference on Computational Linguistics, pages 9992–10020, Abu Dhabi, UAE. Association for Computational Linguistics.
Cite (Informal):
Decoding Decoded: Understanding Hyperparameter Effects in Open-Ended Text Generation (Garces Arias et al., COLING 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.coling-main.668.pdf