activity
20242026
collaborators

17 papers

cs.HC2026

The Hidden Cost of Contextual Sycophancy: an AI Literacy Intervention in Human-AI Collaboration

Cansu Koyuturk, Sabrina Guidotti, Dimitri Ognibene

Large Language Models (LLMs) are increasingly used in educational settings as interactive tools for collaboration. However, their tendency toward sycophancy, aligning with user bel…

cs.RO2025

PerspAct: Enhancing LLM Situated Collaboration Skills through Perspective Taking and Active Vision

Sabrina Patania, Luca Annese, Anita Pellegrini +8

Recent advances in Large Language Models (LLMs) and multimodal foundation models have significantly broadened their application in robotics and collaborative systems. However, effe…

cs.CL2025

Growing Perspectives: Modelling Embodied Perspective Taking and Inner Narrative Development Using Large Language Models

Sabrina Patania, Luca Annese, Anna Lambiase +6

Language and embodied perspective taking are essential for human collaboration, yet few computational models address both simultaneously. This work investigates the PerspAct system…

cs.AI2025

Who Sees What? Structured Thought-Action Sequences for Epistemic Reasoning in LLMs

Luca Annese, Sabrina Patania, Silvia Serino +4

Recent advances in large language models (LLMs) and reasoning frameworks have opened new possibilities for improving the perspective -taking capabilities of autonomous agents. Howe…

cs.CL2025

AI Pedagogy: Dialogic Social Learning for Artificial Agents

Sabrina Patania, Luca Annese, Cansu Koyuturk +2

Large Language Models (LLMs) have demonstrated remarkable capabilities in processing extensive offline datasets. However, they often face challenges in acquiring and integrating co…

cs.HC2025

Understanding Learner-LLM Chatbot Interactions and the Impact of Prompting Guidelines

Cansu Koyuturk, Emily Theophilou, Sabrina Patania +13

Large Language Models (LLMs) have transformed human-computer interaction by enabling natural language-based communication with AI-powered chatbots. These models are designed to be…