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

arXiv: https://arxiv.org/abs/2505.24613 · HTML: https://mlsanity.com/paper/2505.24613/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 42 references that are in the map.
- First posted on arXiv 30 May 2025.

## Builds on (most cited first, 23 of 23)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [Ignore Previous Prompt: Attack Techniques For Language Models](https://mlsanity.com/paper/2211.09527/) (2022)
- [Personalizing Dialogue Agents: I have a dog, do you have pets too?](https://mlsanity.com/paper/1801.07243/) (2018)
- [Scaling Synthetic Data Creation with 1,000,000,000 Personas](https://mlsanity.com/paper/2406.20094/) (2024)
- [Character-LLM: A Trainable Agent for Role-Playing](https://mlsanity.com/paper/2310.10158/) (2023)
- [From Persona to Personalization: A Survey on Role-Playing Language Agents](https://mlsanity.com/paper/2404.18231/) (2024)
- [Two Tales of Persona in LLMs: A Survey of Role-Playing and Personalization](https://mlsanity.com/paper/2406.01171/) (2024)
- [InCharacter: Evaluating Personality Fidelity in Role-Playing Agents through Psychological Interviews](https://mlsanity.com/paper/2310.17976/) (2023)
- [Augmented SBERT: Data Augmentation Method for Improving Bi-Encoders for Pairwise Sentence Scoring Tasks](https://mlsanity.com/paper/2010.08240/) (2020)
- [The Good, The Bad, and The Greedy: Evaluation of LLMs Should Not Ignore Non-Determinism](https://mlsanity.com/paper/2407.10457/) (2024)
- [Large Language Models are Superpositions of All Characters: Attaining Arbitrary Role-play via Self-Alignment](https://mlsanity.com/paper/2401.12474/) (2024)
- [You Impress Me: Dialogue Generation via Mutual Persona Perception](https://mlsanity.com/paper/2004.05388/) (2020)
- [Evaluating the Susceptibility of Pre-Trained Language Models via Handcrafted Adversarial Examples](https://mlsanity.com/paper/2209.02128/) (2022)
- [Measuring and Controlling Instruction (In)Stability in Language Model Dialogs](https://mlsanity.com/paper/2402.10962/) (2024)
- [Neeko: Leveraging Dynamic LoRA for Efficient Multi-Character Role-Playing Agent](https://mlsanity.com/paper/2402.13717/) (2024)
- [From Role-Play to Drama-Interaction: An LLM Solution](https://mlsanity.com/paper/2405.14231/) (2024)
- [COSPLAY: Concept Set Guided Personalized Dialogue Generation Across Both Party Personas](https://mlsanity.com/paper/2205.00872/) (2022)
- [Bias and Fairness in Chatbots: An Overview](https://mlsanity.com/paper/2309.08836/) (2023)
- [PRODIGy: a PROfile-based DIalogue Generation dataset](https://mlsanity.com/paper/2311.05195/) (2023)
- [Partner Matters! An Empirical Study on Fusing Personas for Personalized Response Selection in Retrieval-Based Chatbots](https://mlsanity.com/paper/2105.09050/) (2021)
- [Countering Misinformation via Emotional Response Generation](https://mlsanity.com/paper/2311.10587/) (2023)

## Built on by (most cited first, 4 of 4)

- [Assessing the Reliability of Persona-Conditioned LLMs as Synthetic Survey Respondents](https://mlsanity.com/paper/2602.18462/) (2026)
- [How to Ask the AI: A User Perspective Survey for Large Language Model Prompting](https://mlsanity.com/paper/2608.07494/) (2026)
- [Beyond Individual Personas: Aligning Synthetic Dialogue to Population-Level Behavior Distributions](https://mlsanity.com/paper/2606.07893/) (2026)
- [Stranger, Fan, or Peer? A Systematic Study on the Role of Interlocutor in Persona-Based Dialogue Generation](https://mlsanity.com/paper/2608.28467/) (2026)

## Abstract (arXiv)

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 the 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.