# Designing Conversations with the Dead: How People Engage with Generative Ghosts

arXiv: https://arxiv.org/abs/2605.21390 · HTML: https://mlsanity.com/paper/2605.21390/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 3 of its 45 references that are in the map.
- First posted on arXiv 20 May 2026.

## Builds on (most cited first, 3 of 3)

- [Generative Ghosts: Anticipating Benefits and Risks of AI Afterlives](https://mlsanity.com/paper/2402.01662/) (2024)
- ["AI Afterlife" as Digital Legacy: Perceptions, Expectations, and Concerns](https://mlsanity.com/paper/2502.10924/) (2025)
- [From Personal Data to Digital Legacy: Exploring Conflicts in the Sharing, Security and Privacy of Post-mortem Data](https://mlsanity.com/paper/2104.07807/) (2021)

## Abstract (arXiv)

We examine how people experience two choices in the design of generative ghosts, AI systems that are trained on data of the dead: representation, where an AI speaks about a deceased person in the third person, and reincarnation, where the AI speaks as the deceased in the first person. Through a qualitative user study with 16 participants, we explore how each shaped authenticity, affect, and risk. Reincarnation was preferred for its immediacy, but participants shared fears of over-reliance. Representation was preferred for engaging with memory over conversational presence, though participants often ignored this distinction, engaging in dialogue despite third-person framing. Across both modes, participants privileged affective resonance over factual fidelity. We conclude by showing how factors such as tone, language, and conversational rhythm -- factors unique to the user's memory of the deceased -- shape interactions with generative ghosts, and argue that those interactions are always collaborative.