8 papers
LLM-as-a-Demographic: Whom Sociodemographic Prompting Helps, and Whom It Hurts
Daniela Occhipinti, Andrea Piergentili, Marco Guerini
Large language models (LLMs) are increasingly used as judges for subjective tasks, where annotators disagree and the relevant question is not only how accurate a judge is, but whos…
Stranger, Fan, or Peer? A Systematic Study on the Role of Interlocutor in Persona-Based Dialogue Generation
Daniela Occhipinti, Malvina Nissim, Marco Guerini
Persona-based dialogue systems are usually conditioned on speaker biography, but dialogues involve at least two participants, and who has access to whose biography can vary across…
CATCH-ME if you RAG: a dataset of Contextually Annotated multi-Turn Counterspeech against Hate and Misinformation Exchanges
Helena Bonaldi, Genoveffa Martone, Marco Guerini
Online hate speech and misinformation frequently overlap, yet NLP research has mainly treated them in isolation. While LLMs represent a scalable solution for assisting humans in th…
Guide Me Out: A Framework to Benchmark VLM Operators Communication in Crisis Scenarios
Giacomo Gonella, Stefano Menini, Marco Guerini
Effective crisis response requires spatially grounded communication that bridges linguistic guidance of civilians with the physical environment, accounting for structural bottlenec…
Assisted Counterspeech Writing at the Crossroads of Hate Speech and Misinformation
Genoveffa Martone, Helena Bonaldi, Marco Guerini
Hate speech and misinformation frequently co-occur online, amplifying prejudice and polarization. Given their scale, using Large Language Models (LLMs) to assist expert counterspee…
When Harry Meets Superman: The Role of The Interlocutor in Persona-Based Dialogue Generation
Daniela Occhipinti, Marco Guerini, Malvina Nissim
Endowing dialogue agents with persona information has proven to significantly improve the consistency and diversity of their generations. While much focus has been placed on aligni…
Fine-tuning with HED-IT: The impact of human post-editing for dialogical language models
Daniela Occhipinti, Michele Marchi, Irene Mondella +4
Automatic methods for generating and gathering linguistic data have proven effective for fine-tuning Language Models (LMs) in languages less resourced than English. Still, while th…
PRODIGy: a PROfile-based DIalogue Generation dataset
Daniela Occhipinti, Serra Sinem Tekiroglu, Marco Guerini
Providing dialogue agents with a profile representation can improve their consistency and coherence, leading to better conversations. However, current profile-based dialogue datase…