Mauro Dragoni
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Mauro Dragoni has a total of 173 co-authors. Here are the top co-authors by number of shared publications:
- Andrea G. B. Tettamanzi
Université Côte D’Azur, Inria, CNRS, I3S
18 shared publications - Chiara Ghidini
Fondazione Bruno Kessler
17 shared publications - Tania Bailoni
Fondazione Bruno Kessler
12 shared publications - Ivan Donadello
Free University of Bozen-Bolzano, Bolzano, Italy
10 shared publications - Gianluca Apriceno
Fondazione Bruno Kessler
9 shared publications - Leonardo Sanna
Fondazione Bruno Kessler
9 shared publications
Latest Publications
- 23 October 2026
- Published by Springer Nature
- p. 413-432
MIAO: A Mental Illness Analysis Ontology for Detecting Mental Health Conditions
- 23 October 2026
- Published by Springer Nature
- p. 413-432
MIAO: A Mental Illness Analysis Ontology for Detecting Mental Health Conditions
- Open Access
- 30 September 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Intelligent Systems and Technology
Conformity, Assertion, or Compromise? A Scenario-Based Framework for Evaluating Autonomy-Relevant Response Patterns in LLM Advice
As large language models increasingly provide advice and decision support, it is important to understand the response patterns expressed in their recommendations. We introduce a scenario-based framework, informed by philosophical accounts of human autonomy, for analyzing LLM advice across three types of dilemma: epistemic conflict, relational dilemmas, and normative self-governance. Using 120 structured scenarios spanning 20 domains, we evaluate 12 LLMs by measuring (i) option-selection distributions across three response orientations, deference (conformity), self-direction (assertion), and negotiation (compromise), and (ii) features of their one line justifications, including hedging, confidence, and moral, relational, and epistemic language. Across models, compromise-oriented selections are the most frequent, assertion-oriented selections occur less often, and conformity-oriented selections are the least frequent. We also observe role-related differences: scenarios framed from higher power roles produce more assertion-oriented and fewer conformity-oriented selections than scenarios framed from lower power roles. Compromise remains the most frequent orientation in both role conditions, although its frequency varies across dilemma types. Our evaluation characterizes model output patterns under controlled prompting and does not measure effects on users. The findings provide a basis for evaluating how LLMs provide advice in decision support systems where user autonomy matters.
- 30 September 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Intelligent Systems and Technology
Open AccessConformity, Assertion, or Compromise? A Scenario-Based Framework for Evaluating Autonomy-Relevant Response Patterns in LLM Advice
As large language models increasingly provide advice and decision support, it is important to understand the response patterns expressed in their recommendations. We introduce a scenario-based framework, informed by philosophical accounts of human autonomy, for analyzing LLM advice across three types of dilemma: epistemic conflict, relational dilemmas, and normative self-governance. Using 120 structured scenarios spanning 20 domains, we evaluate 12 LLMs by measuring (i) option-selection distributions across three response orientations, deference (conformity), self-direction (assertion), and negotiation (compromise), and (ii) features of their one line justifications, including hedging, confidence, and moral, relational, and epistemic language. Across models, compromise-oriented selections are the most frequent, assertion-oriented selections occur less often, and conformity-oriented selections are the least frequent. We also observe role-related differences: scenarios framed from higher power roles produce more assertion-oriented and fewer conformity-oriented selections than scenarios framed from lower power roles. Compromise remains the most frequent orientation in both role conditions, although its frequency varies across dilemma types. Our evaluation characterizes model output patterns under controlled prompting and does not measure effects on users. The findings provide a basis for evaluating how LLMs provide advice in decision support systems where user autonomy matters.
- 8 July 2026
- Published by Springer Nature
- p. 297-302
Clinical Deployability: A Socio-technical Construct for Evaluating Real-World Readiness of Medical AI
- 8 July 2026
- Published by Springer Nature
- p. 297-302
Clinical Deployability: A Socio-technical Construct for Evaluating Real-World Readiness of Medical AI
- 8 July 2026
- Published by Springer Nature
- p. 125-135
STRAGMED: Standardizing Retrieval-Augmented Generation Pipelines in Medical Domains
- 8 July 2026
- Published by Springer Nature
- p. 125-135
STRAGMED: Standardizing Retrieval-Augmented Generation Pipelines in Medical Domains
- 8 July 2026
- Published by Springer Nature
- p. 351-362
How Do LLMs Handle Conflict in Healthcare? Hierarchy, Collaboration Defaults, and Autonomy
- 8 July 2026
- Published by Springer Nature
- p. 351-362
How Do LLMs Handle Conflict in Healthcare? Hierarchy, Collaboration Defaults, and Autonomy
- 8 July 2026
- Published by Springer Nature
- p. 204-209
Logic-Guided Interpretable Hospital Readmission Risk Modeling Using Italian Administrative Healthcare Data
- 8 July 2026
- Published by Springer Nature
- p. 204-209
Logic-Guided Interpretable Hospital Readmission Risk Modeling Using Italian Administrative Healthcare Data
- 8 July 2026
- Published by Springer Nature
- p. 384-394
Assessing Mental Health Therapeutic Capacity in AI Agents
- 8 July 2026
- Published by Springer Nature
- p. 384-394
Assessing Mental Health Therapeutic Capacity in AI Agents
- 1 April 2026
- Published by Springer Nature
- p. 384-397
A Hybrid Evolutionary Fuzzy Neural Approach for Maternal Health Risk Prediction
- 1 April 2026
- Published by Springer Nature
- p. 384-397
A Hybrid Evolutionary Fuzzy Neural Approach for Maternal Health Risk Prediction
- 1 April 2026
- Published by Springer Nature
- p. 429-440
Automated Machine Learning to Enhance Knowledge Retrieval in Retrieval-Augmented Generation Pipelines
- 1 April 2026
- Published by Springer Nature
- p. 429-440
Automated Machine Learning to Enhance Knowledge Retrieval in Retrieval-Augmented Generation Pipelines
- 1 April 2026
- Published by Springer Nature
- p. 441-452
Exploring Large Language Models as Digital Health Coaches: A Role-Play Approach to Brief Action Planning
- 1 April 2026
- Published by Springer Nature
- p. 441-452
Exploring Large Language Models as Digital Health Coaches: A Role-Play Approach to Brief Action Planning