-----------------

Apologies for cross-posting.

-----------------

The Language and Dialogue Technologies (LanD https://land.fbk.eu/) group at Fondazione Bruno Kessler https://www.fbk.eu/en/ (Trento, Italy) in conjunction with the ICT International Doctorate School of the University of Trento https://iecs.unitn.it/ is pleased to announce the availability of two fully-funded PhD position:

*1) TITLE*: *Integrating Values, Beliefs, and Social Dynamics into Conversational Agents*

*DESCRIPTION*: Providing neural models with a persona profile has demonstrated that conditioning such models on specific characteristics produces more coherent and engaging conversations. However, current representations remain shallow, typically relying on static biographical facts. In reality, human communication is shaped by both profound internal traits - such as goals, opinions, values, and beliefs - and dynamic situational factors, including emotional states, conversational context, and the specific relationship between speakers. The goal of this PhD Thesis is to bridge these dimensions, moving beyond rigid profiles to develop adaptive, context-sensitive persona models. By integrating deep profile characteristics with real-time social dynamics, the research aims to advance the state of language generation for conversational agents across multiple domains and languages. *Link to the call*: https://iecs.unitn.it/education/admission/reserved-topic-scholarships#A5

*2) TITLE*: *Knowledge-Driven Natural Language Generation for Combating Hateful Misinformation*

*DESCRIPTION*: The convergence of online misinformation and hate speech poses a significant threat to social cohesion, especially when manipulated content is used to incite hostility toward marginalized groups. While large language models (LLMs) offer potential for fact-checking and counterspeech, current systems often struggle with factual accuracy, complex reasoning, and the nuanced social dynamics of harmful content. This PhD project aims to overcome these hurdles by developing knowledge-enhanced neural generation frameworks. The research will integrate external knowledge and computational argumentation to produce reliable, persuasive, and ethically grounded responses, while also addressing the moral values and motivations of users spreading hate-based misinformation. Ultimately, this work seeks to advance generative AI that can mitigate harmful discourse and clarify its underlying mechanisms. *Link to the call*: https://iecs.unitn.it/education/admission/reserved-topic-scholarships#A6

*COMPLETE DETAILS AVAILABLE AT*: https://iecs.unitn.it/education/admission/call-for-application

*IMPORTANT DATES:* deadline for application is 27th August 2026, hrs. 04:00 PM (CEST)

*FURTHER INFORMATION:* For preliminary interviews, and should you need further information about the position, please contact me (guerini@fbk.eu)

Best Regards,

Marco Guerini