Copertina

How LLMs Follow Instructions: Skillful Coordination, Not a Universal Mechanism

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Rocchetti, Elisabetta, Ferrara, Alfio
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

How Instruction-Tuning Imparts Length Control: A Cross-Lingual Mechanistic Analysis
di: Rocchetti, Elisabetta, et al.
Pubblicazione: (2025)

Unveiling Transformer Perception by Exploring Input Manifolds
di: Benfenati, Alessandro, et al.
Pubblicazione: (2024)

Modeling Transformers as complex networks to analyze learning dynamics
di: Rocchetti, Elisabetta
Pubblicazione: (2025)

The Cow of Rembrandt - Analyzing Artistic Prompt Interpretation in Text-to-Image Models
di: Ferrara, Alfio, et al.
Pubblicazione: (2025)

How Many Instructions Can LLMs Follow at Once?
di: Jaroslawicz, Daniel, et al.
Pubblicazione: (2025)

What's Taboo for You? - An Empirical Evaluation of LLMs Behavior Toward Sensitive Content
di: Ferrara, Alfio, et al.
Pubblicazione: (2025)

Neuro-Symbolic Verification on Instruction Following of LLMs
di: Su, Yiming, et al.
Pubblicazione: (2026)

The Instruction Gap: LLMs get lost in Following Instruction
di: Tripathi, Vishesh, et al.
Pubblicazione: (2025)

Autonomous Improvement of Instruction Following Skills via Foundation Models
di: Zhou, Zhiyuan, et al.
Pubblicazione: (2024)

Semantic Skill Grounding for Embodied Instruction-Following in Cross-Domain Environments
di: Shin, Sangwoo, et al.
Pubblicazione: (2024)

Transcription and Recognition of Italian Parliamentary Speeches Using Vision-Language Models
di: Curini, Luigi, et al.
Pubblicazione: (2026)

Thinking LLMs: General Instruction Following with Thought Generation
di: Wu, Tianhao, et al.
Pubblicazione: (2024)

Is In-Context Learning Sufficient for Instruction Following in LLMs?
di: Zhao, Hao, et al.
Pubblicazione: (2024)

RECAST: Expanding the Boundaries of LLMs' Complex Instruction Following with Multi-Constraint Data
di: Guo, Zhengkang, et al.
Pubblicazione: (2025)

Synthetic Consciousness Emergence Protocol (SCEP) — Universal Neutral Version
di: Elisabetta, Palazzi
Pubblicazione: (2025)

Enhancing Instruction Following of LLMs via Activation Steering with Dynamic Rejection
di: Kang, Minjae, et al.
Pubblicazione: (2026)

LLM CHESS: Benchmarking Reasoning and Instruction-Following in LLMs through Chess
di: Kolasani, Sai, et al.
Pubblicazione: (2025)

The End of Reward Engineering: How LLMs Are Redefining Multi-Agent Coordination
di: Su, Haoran, et al.
Pubblicazione: (2026)

Boosting Instruction Following at Scale
di: Elder, Ben, et al.
Pubblicazione: (2025)

RIFT: Reordered Instruction Following Testbed To Evaluate Instruction Following in Singular Multistep Prompt Structures
di: Jaffe, Andrew, et al.
Pubblicazione: (2026)

Empowering Persian LLMs for Instruction Following: A Novel Dataset and Training Approach
di: Mokhtarabadi, Hojjat, et al.
Pubblicazione: (2024)

From Language Modeling to Instruction Following: Understanding the Behavior Shift in LLMs after Instruction Tuning
di: Wu, Xuansheng, et al.
Pubblicazione: (2023)

How Reliable Are Automatic Evaluation Methods for Instruction-Tuned LLMs?
di: Doostmohammadi, Ehsan, et al.
Pubblicazione: (2024)

IOPO: Empowering LLMs with Complex Instruction Following via Input-Output Preference Optimization
di: Zhang, Xinghua, et al.
Pubblicazione: (2024)

Quid est VERITAS? A Modular Framework for Archival Document Analysis
di: Bassanini, Leonardo, et al.
Pubblicazione: (2026)

Embodied Instruction Following in Unknown Environments
di: Wu, Zhenyu, et al.
Pubblicazione: (2024)

Situated Instruction Following
di: Min, So Yeon, et al.
Pubblicazione: (2024)

MUFFIN: Curating Multi-Faceted Instructions for Improving Instruction-Following
di: Lou, Renze, et al.
Pubblicazione: (2023)

U-MATH: A University-Level Benchmark for Evaluating Mathematical Skills in LLMs
di: Chernyshev, Konstantin, et al.
Pubblicazione: (2024)

Training with Pseudo-Code for Instruction Following
di: Kumar, Prince, et al.
Pubblicazione: (2025)

WildIFEval: Instruction Following in the Wild
di: Lior, Gili, et al.
Pubblicazione: (2025)

SearchSkill: Teaching LLMs to Use Search Tools with Evolving Skill Banks
di: Hu, Jinchao, et al.
Pubblicazione: (2026)

Enhancing LLM Instruction Following: An Evaluation-Driven Multi-Agentic Workflow for Prompt Instructions Optimization
di: Purpura, Alberto, et al.
Pubblicazione: (2026)

Exploratory Retrieval-Augmented Planning For Continual Embodied Instruction Following
di: Yoo, Minjong, et al.
Pubblicazione: (2025)

Instruction-Following Evaluation in Function Calling for Large Language Models
di: Skripko, Nikolai
Pubblicazione: (2025)

Instruction Following with Goal-Conditioned Reinforcement Learning in Virtual Environments
di: Volovikova, Zoya, et al.
Pubblicazione: (2024)

Semantic Trading: Agentic AI for Clustering and Relationship Discovery in Prediction Markets
di: Capponi, Agostino, et al.
Pubblicazione: (2025)

Following the Whispers of Values: Unraveling Neural Mechanisms Behind Value-Oriented Behaviors in LLMs
di: Hu, Ling, et al.
Pubblicazione: (2025)

Multi-Level Compositional Reasoning for Interactive Instruction Following
di: Bhambri, Suvaansh, et al.
Pubblicazione: (2023)

Verifiably Following Complex Robot Instructions with Foundation Models
di: Quartey, Benedict, et al.
Pubblicazione: (2024)