Daniela
Occhipinti

2026

1. EMNLP2026

   Stranger, Fan, or Peer? A Systematic Study on the Role of Interlocutor in Persona-Based Dialogue Generation

   Daniela Occhipinti, Malvina Nissim, and Marco Guerini

   In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, Oct 2026

   Examines how access to biographies during training, generation and evaluation shapes contextual adaptation, copying and information leakage in persona-based dialogue.

   PDF ↗

   Abstract

   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 training, inference, and evaluation. Prior work often neglected these aspects, obscuring mechanisms that only appear when biography visibility is toggled separately across training, inference, and evaluation, a three-stage factorisation that prior work has largely treated as a single factor. We study this factorisation on a dataset of dialogues paired with speakers’ biographies, varying whether the target and interlocutor speakers see each other’s biographies during training and inference, and using an LLM as a judge to perform author identification. We find that (i) training-time visibility, more than inference-time visibility, determines whether models express persona traits through dialogue or fall back on copying biographical text (a known problem/phenomenon in persona-based generation); (ii) models trained with interlocutor-biography visibility copy less target-biographical text than models trained without it, while changing visibility only at inference time has a less consistent effect; and (iii) under asymmetric disclosure, where only the interlocutor sees the target biography, target content leaks into interlocutor turns more often, and dialogues containing such traces are easier for the judge to identify, especially when interlocutor turns are visible. In the setting we study, these results suggest that biography leakage into generated turns is largely an artefact of how interlocutor visibility is configured across training and inference, and separating the three stages is necessary to observe it.

   Bib

   @inproceedings{occhipinti-etal-2026-stranger,
     title = {Stranger, Fan, or Peer? A Systematic Study on the Role of Interlocutor in Persona-Based Dialogue Generation},
     author = {Occhipinti, Daniela and Nissim, Malvina and Guerini, Marco},
     booktitle = {Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing},
     month = oct,
     year = {2026},
     publisher = {Association for Computational Linguistics},
     pages = {10250--10270},
     url = {https://aclanthology.org/2026.emnlp-main.445/},
     note = {Examines how access to biographies during training, generation and evaluation shapes contextual adaptation, copying and information leakage in persona-based dialogue.}
   }
   

2025

1. ACL2025

   When Harry Meets Superman: The Role of The Interlocutor in Persona-Based Dialogue Generation

   Daniela Occhipinti, Marco Guerini, and Malvina Nissim

   In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Jul 2025

   Explores how dialogue generation changes when models know not just who is speaking, but who they are speaking to — and what that relationship means for consistency.

   PDF ↗ DOI ↗

   Abstract

   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 aligning dialogues with provided personas, the adaptation to the interlocutor’s profile remains largely underexplored. In this work, we investigate three key aspects: (1) a model’s ability to align responses with both the provided persona and the interlocutor’s; (2) its robustness when dealing with familiar versus unfamiliar interlocutors and topics, and (3) the impact of additional fine-tuning on specific persona-based dialogues. We evaluate dialogues generated with diverse speaker pairings and topics, framing the evaluation as an author identification task and employing both LLM-as-a-judge and human evaluations. By systematically masking or disclosing information about interlocutor, we assess its impact on dialogue generation. Results show that access to the interlocutor’s persona improves the recognition of the target speaker, while masking it does the opposite. Although models generalise well across topics, they struggle with unfamiliar interlocutors. Finally, we found that in zero-shot settings, LLMs often copy biographical details, facilitating identification but trivialising the task.

   Bib

   @inproceedings{occhipinti-etal-2025-superman,
     title = {When Harry Meets Superman: The Role of The Interlocutor in Persona-Based Dialogue Generation},
     author = {Occhipinti, Daniela and Guerini, Marco and Nissim, Malvina},
     editor = {Che, Wanxiang and Nabende, Joyce and Shutova, Ekaterina and Pilehvar, Mohammad Taher},
     booktitle = {Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
     month = jul,
     year = {2025},
     address = {Vienna, Austria},
     publisher = {Association for Computational Linguistics},
     url = {https://aclanthology.org/2025.acl-long.879/},
     doi = {10.18653/v1/2025.acl-long.879},
     pages = {17964--17985},
     isbn = {979-8-89176-251-0},
     note = {Explores how dialogue generation changes when models know not just who is speaking, but who they are speaking to — and what that relationship means for consistency.},
   }