Copertina

Are LLMs Ready for TOON? Benchmarking Structural Correctness-Sustainability Trade-offs in Novel Structured Output Formats

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Masciari, Elio, Moscato, Vincenzo, Napolitano, Enea Vincenzo, Orlando, Gian Marco, Perillo, Marco, Russo, Diego
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Artificial Intelligence Software Engineering
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

A Brief Discussion on KPI Development in Public Administration
di: Fioretto, Simona, et al.
Pubblicazione: (2024)

Predictive Process Monitoring: a comparison survey between different type of event logs
di: Fioretto, Simona, et al.
Pubblicazione: (2025)

From Who They Are to How They Act: Behavioral Traits in Generative Agent-Based Models of Social Media
di: La Gatta, Valerio, et al.
Pubblicazione: (2026)

Automating AI Failure Tracking: Semantic Association of Reports in AI Incident Database
di: Russo, Diego, et al.
Pubblicazione: (2025)

Can Generative Agent-Based Modeling Replicate the Friendship Paradox in Social Media Simulations?
di: Orlando, Gian Marco, et al.
Pubblicazione: (2025)

Helping LLMs Improve Code Generation Using Feedback from Testing and Static Analysis
di: Dolcetti, Greta, et al.
Pubblicazione: (2024)

StructEval: Benchmarking LLMs' Capabilities to Generate Structural Outputs
di: Yang, Jialin, et al.
Pubblicazione: (2025)

Assessing the Potential of Generative Agents in Crowdsourced Fact-Checking
di: Costabile, Luigia, et al.
Pubblicazione: (2025)

Unveiling Competition Dynamics in Mobile App Markets through User Reviews
di: Motger, Quim, et al.
Pubblicazione: (2023)

Toward an Architectural Blueprint to Observe Sustainability in and by Software Systems
di: Toczé, Klervie, et al.
Pubblicazione: (2026)

Evaluating LLM-Based Mobile App Recommendations: An Empirical Study
di: Motger, Quim, et al.
Pubblicazione: (2025)

The Constraint Tax: Measuring Validity-Correctness Tradeoffs in Structured Outputs for Small Language Models
di: Ray, Jaideep
Pubblicazione: (2026)

To Diff or Not to Diff? Structure-Aware and Adaptive Output Formats for Efficient LLM-based Code Editing
di: Cheng, Wei, et al.
Pubblicazione: (2026)

Agent-Based Modelling Meets Generative AI in Social Network Simulations
di: Ferraro, Antonino, et al.
Pubblicazione: (2024)

What Is the Cost of Energy Monitoring? An Empirical Study on the Overhead of RAPL-Based Tools
di: Diamond, Jeremy, et al.
Pubblicazione: (2026)

An Empirical Study on How Architectural Topology Affects Microservice Performance and Energy Usage
di: Ristova, Irena, et al.
Pubblicazione: (2026)

Classification, Challenges, and Automated Approaches to Handle Non-Functional Requirements in ML-Enabled Systems: A Systematic Literature Review
di: De Martino, Vincenzo, et al.
Pubblicazione: (2023)

A Framework for Using LLMs for Repository Mining Studies in Empirical Software Engineering
di: de Martino, Vincenzo, et al.
Pubblicazione: (2024)

Engineering Trustworthy Software: A Mission for LLMs
di: Vieira, Marco
Pubblicazione: (2024)

Benchmarking Generative AI Models for Deep Learning Test Input Generation
di: Maryam, et al.
Pubblicazione: (2024)

Beyond Monolithic Models: Symbolic Seams for Composable Neuro-Symbolic Architectures
di: Schuler, Nicolas, et al.
Pubblicazione: (2026)

Performance Antipatterns: Angel or Devil for Power Consumption?
di: Aneggi, Alessandro, et al.
Pubblicazione: (2026)

A Large-Scale Study of Call Graph-based Impact Prediction using Mutation Testing
di: Musco, Vincenzo, et al.
Pubblicazione: (2018)

Exploring Performance Trade-offs in JHipster
di: Guégain, Edouard, et al.
Pubblicazione: (2024)

IMB: An Italian Medical Benchmark for Question Answering
di: Romano, Antonio, et al.
Pubblicazione: (2025)

Digital Twins & ZeroConf AI: Structuring Automated Intelligent Pipelines for Industrial Applications
di: Picone, Marco, et al.
Pubblicazione: (2026)

Sustainability of Machine Learning-Enabled Systems: The Machine Learning Practitioner's Perspective
di: De Martino, Vincenzo, et al.
Pubblicazione: (2025)

Financial Twin Chain, a Platform to Support Financial Sustainability in Supply Chains
di: Galante, Giuseppe, et al.
Pubblicazione: (2025)

Comparing Open-Source and Commercial LLMs for Domain-Specific Analysis and Reporting: Software Engineering Challenges and Design Trade-offs
di: Koraag, Theo, et al.
Pubblicazione: (2025)

How to Sustainably Monitor ML-Enabled Systems? Accuracy and Energy Efficiency Tradeoffs in Concept Drift Detection
di: Omar, Rafiullah, et al.
Pubblicazione: (2024)

From Passive to Participatory: How Liberating Structures Can Revolutionize Our Conferences
di: Russo, Daniel, et al.
Pubblicazione: (2025)

Beyond Output Correctness: Benchmarking and Evaluating Large Language Model Reasoning in Coding Tasks
di: Li, Yuangang, et al.
Pubblicazione: (2026)

DART: A Structured Dataset of Regulatory Drug Documents in Italian for Clinical NLP
di: Barone, Mariano, et al.
Pubblicazione: (2025)

Automated Feature Extraction for Testing Deep Learning Systems Through Illumination Search
di: Tahereh Zohdinasab, et al.
Pubblicazione: (2026)

Assessing AI-Based Code Assistants in Method Generation Tasks
di: Corso, Vincenzo, et al.
Pubblicazione: (2024)

Generating Java Methods: An Empirical Assessment of Four AI-Based Code Assistants
di: Corso, Vincenzo, et al.
Pubblicazione: (2024)

Do Developers Adopt Green Architectural Tactics for ML-Enabled Systems? A Mining Software Repository Study
di: De Martino, Vincenzo, et al.
Pubblicazione: (2024)

Green Architectural Tactics in ML-enabled Systems: An LLM-based Repository Mining Study
di: De Martino, Vincenzo, et al.
Pubblicazione: (2026)

Many-Objective Optimization of Non-Functional Attributes based on Refactoring of Software Models
di: Cortellessa, Vittorio, et al.
Pubblicazione: (2023)

The Road to Hybrid Quantum Programs: Characterizing the Evolution from Classical to Hybrid Quantum Software
di: De Maio, Vincenzo, et al.
Pubblicazione: (2025)