Image de couverture de livre

Babbling Suppression: Making LLMs Greener One Token at a Time

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Solovyeva, Lola, Castor, Fernando
Format:	Preprint
Publié:	2026
Sujets:	Software Engineering
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Towards Green AI: Decoding the Energy of LLM Inference in Software Development
par: Solovyeva, Lola, et autres
Publié: (2026)

AI-Powered, But Power-Hungry? Energy Efficiency of LLM-Generated Code
par: Solovyeva, Lola, et autres
Publié: (2025)

Leveraging LLMs for Automated Translation of Legacy Code: A Case Study on PL/SQL to Java Transformation
par: Solovyeva, Lola, et autres
Publié: (2025)

Estimating the Energy Footprint of Software Systems: a Primer
par: Castor, Fernando
Publié: (2024)

Token Sugar: Making Source Code Sweeter for LLMs through Token-Efficient Shorthand
par: Sun, Zhensu, et autres
Publié: (2025)

Green AI: A Preliminary Empirical Study on Energy Consumption in DL Models Across Different Runtime Infrastructures
par: Alizadeh, Negar, et autres
Publié: (2024)

An Initial Exploration of Contrastive Prompt Tuning to Generate Energy-Efficient Code
par: Weidmann, Sophie, et autres
Publié: (2026)

Language Models in Software Development Tasks: An Experimental Analysis of Energy and Accuracy
par: Alizadeh, Negar, et autres
Publié: (2024)

Fuzz Smarter, Not Harder: Towards Greener Fuzzing with GreenAFL
par: Ercevik, Ayse Irmak, et autres
Publié: (2025)

GA4GC: Greener Agent for Greener Code via Multi-Objective Configuration Optimization
par: Gong, Jingzhi, et autres
Publié: (2025)

Toward Greener Background Processes -- Measuring Energy Cost of Autosave Feature
par: Küüsvek, Maria, et autres
Publié: (2025)

Understanding Code Understandability Improvements in Code Reviews
par: Oliveira, Delano, et autres
Publié: (2024)

Impact of ML Optimization Tactics on Greener Pre-Trained ML Models
par: Álvarez, Alexandra González, et autres
Publié: (2024)

A framework for assessing the capabilities of code generation of constraint domain-specific languages with large language models
par: Delgado, David, et autres
Publié: (2026)

Understanding Underrepresented Groups in Open Source Software
par: Santos, Reydne, et autres
Publié: (2025)

When to Stop? Towards Efficient Code Generation in LLMs with Excess Token Prevention
par: Guo, Lianghong, et autres
Publié: (2024)

What Makes Good In-context Demonstrations for Code Intelligence Tasks with LLMs?
par: Gao, Shuzheng, et autres
Publié: (2023)

Optimizing Token Consumption in LLMs: A Nano Surge Approach for Code Reasoning Efficiency
par: Hu, Junwei, et autres
Publié: (2025)

A Benchmarking Framework for Model Datasets
par: Glaser, Philipp-Lorenz, et autres
Publié: (2026)

LLM-based Generation of Semantically Diverse and Realistic Domain Model Instances
par: Coman, Andrei, et autres
Publié: (2026)

Detecting Semantic Alignments between Textual Specifications and Domain Models
par: Shimangaud, Shwetali, et autres
Publié: (2026)

Exploring Actions, Interactions and Challenges in Software Modelling Tasks: An Empirical Investigation with Students
par: Chakraborty, Shalini, et autres
Publié: (2024)

Automation in Model-Driven Engineering: A look back, and ahead
par: Burgueño, Lola, et autres
Publié: (2024)

Mind the Ethics! The Overlooked Ethical Dimensions of GenAI in Software Modeling Education
par: Chakraborty, Shalini, et autres
Publié: (2025)

Decoding Secret Memorization in Code LLMs Through Token-Level Characterization
par: Nie, Yuqing, et autres
Publié: (2024)

One Size Fits All? An Empirical Comparison of ADR Templates regarding Comprehension, Usability, and Ease of Adoption
par: Nogueira, Fernando, et autres
Publié: (2026)

What Makes a Good TODO Comment?
par: Wang, Haoye, et autres
Publié: (2025)

An Empirical Study of Token-based Micro Commits
par: Kondo, Masanari, et autres
Publié: (2024)

Enabling Global, Human-Centered Explanations for LLMs:From Tokens to Interpretable Code and Test Generation
par: Khati, Dipin, et autres
Publié: (2025)

One Bug, Hundreds Behind: LLMs for Large-Scale Bug Discovery
par: Wu, Qiushi, et autres
Publié: (2025)

LLMs-Powered Real-Time Fault Injection: An Approach Toward Intelligent Fault Test Cases Generation
par: Abboush, Mohammad, et autres
Publié: (2025)

Feature Importance in the Context of Traditional and Just-In-Time Software Defect Prediction Models
par: Haldar, Susmita, et autres
Publié: (2024)

On the Effect of Token Merging on Pre-trained Models for Code
par: Saad, Mootez, et autres
Publié: (2025)

What Makes a GitHub Issue Ready for Copilot?
par: Sayagh, Mohammed
Publié: (2025)

What Makes a Great Software Quality Assurance Engineer?
par: Farias, Roselane Silva, et autres
Publié: (2024)

Peeling Off the Cocoon: Unveiling Suppressed Golden Seeds for Mutational Greybox Fuzzing
par: Qian, Ruixiang, et autres
Publié: (2026)

CodeTF: One-stop Transformer Library for State-of-the-art Code LLMs
par: Bui, Nghi D. Q., et autres
Publié: (2023)

LogFold: Compressing Logs with Structured Tokens and Hybrid Encoding
par: Shan, Shiwen, et autres
Publié: (2026)

Reducing Token Usage of State-in-Context Agents using Minification
par: Hrubec, Nicolas, et autres
Publié: (2026)

SkillReducer: Optimizing LLM Agent Skills for Token Efficiency
par: Gao, Yudong, et autres
Publié: (2026)