@inproceedings{xu-etal-2025-ecotune,
title = "{E}co{T}une: Token-Efficient Multi-Fidelity Hyperparameter Optimization for Large Language Model Inference",
author = "Xu, Yuebin and
Chen, Zhiyi and
Wen, Zeyi",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.emnlp-main.394/",
pages = "7746--7756",
ISBN = "979-8-89176-332-6",
abstract = "Tuning inference hyperparameters, such as temperature and maximum output tokens, on downstream tasks can enhance inference performance. However, directly applying hyperparameter optimization to these hyperparameters is token-expensive. Multi-fidelity optimization improves HPO efficiency with low-fidelity evaluations, but its static scheduling strategies ignore token consumption, leading to high costs. To address these limitations, we propose a token-efficient multi-fidelity optimization method, which enhances inference performance and minimizes token usage. Our method is empowered by (i) a token-based fidelity definition with explicit token cost modeling on configurations; (ii) a novel Token-Aware Expected Improvement acquisition function that selects configurations based on performance gain per token; and (iii) a dynamic fidelity scheduling mechanism that adapts to real-time budget status. We evaluate our method on LLaMA-2 and LLaMA-3 series across MMLU, Humaneval, MedQA, and OpenBookQA. Our method improves over the HELM leaderboard by 7.1{\%}, 24.3{\%}, 21.9{\%}, and 4.6{\%}, respectively. Compared to existing multi-fidelity HPO baselines, our method reduces token consumption by over 80{\%} while maintaining or surpassing performance, demonstrating the state-of-the-art token efficiency for inference-time optimization."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xu-etal-2025-ecotune">
<titleInfo>
<title>EcoTune: Token-Efficient Multi-Fidelity Hyperparameter Optimization for Large Language Model Inference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuebin</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhiyi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zeyi</namePart>
<namePart type="family">Wen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-332-6</identifier>
</relatedItem>
<abstract>Tuning inference hyperparameters, such as temperature and maximum output tokens, on downstream tasks can enhance inference performance. However, directly applying hyperparameter optimization to these hyperparameters is token-expensive. Multi-fidelity optimization improves HPO efficiency with low-fidelity evaluations, but its static scheduling strategies ignore token consumption, leading to high costs. To address these limitations, we propose a token-efficient multi-fidelity optimization method, which enhances inference performance and minimizes token usage. Our method is empowered by (i) a token-based fidelity definition with explicit token cost modeling on configurations; (ii) a novel Token-Aware Expected Improvement acquisition function that selects configurations based on performance gain per token; and (iii) a dynamic fidelity scheduling mechanism that adapts to real-time budget status. We evaluate our method on LLaMA-2 and LLaMA-3 series across MMLU, Humaneval, MedQA, and OpenBookQA. Our method improves over the HELM leaderboard by 7.1%, 24.3%, 21.9%, and 4.6%, respectively. Compared to existing multi-fidelity HPO baselines, our method reduces token consumption by over 80% while maintaining or surpassing performance, demonstrating the state-of-the-art token efficiency for inference-time optimization.</abstract>
<identifier type="citekey">xu-etal-2025-ecotune</identifier>
<location>
<url>https://aclanthology.org/2025.emnlp-main.394/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>7746</start>
<end>7756</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T EcoTune: Token-Efficient Multi-Fidelity Hyperparameter Optimization for Large Language Model Inference
%A Xu, Yuebin
%A Chen, Zhiyi
%A Wen, Zeyi
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-332-6
%F xu-etal-2025-ecotune
%X Tuning inference hyperparameters, such as temperature and maximum output tokens, on downstream tasks can enhance inference performance. However, directly applying hyperparameter optimization to these hyperparameters is token-expensive. Multi-fidelity optimization improves HPO efficiency with low-fidelity evaluations, but its static scheduling strategies ignore token consumption, leading to high costs. To address these limitations, we propose a token-efficient multi-fidelity optimization method, which enhances inference performance and minimizes token usage. Our method is empowered by (i) a token-based fidelity definition with explicit token cost modeling on configurations; (ii) a novel Token-Aware Expected Improvement acquisition function that selects configurations based on performance gain per token; and (iii) a dynamic fidelity scheduling mechanism that adapts to real-time budget status. We evaluate our method on LLaMA-2 and LLaMA-3 series across MMLU, Humaneval, MedQA, and OpenBookQA. Our method improves over the HELM leaderboard by 7.1%, 24.3%, 21.9%, and 4.6%, respectively. Compared to existing multi-fidelity HPO baselines, our method reduces token consumption by over 80% while maintaining or surpassing performance, demonstrating the state-of-the-art token efficiency for inference-time optimization.
%U https://aclanthology.org/2025.emnlp-main.394/
%P 7746-7756
Markdown (Informal)
[EcoTune: Token-Efficient Multi-Fidelity Hyperparameter Optimization for Large Language Model Inference](https://aclanthology.org/2025.emnlp-main.394/) (Xu et al., EMNLP 2025)
ACL