Synonymix: Unified Group Personas for Generative Simulations
Huanxing Chen, Aditesh Kumar

TL;DR
Synonymix introduces a meso-level simulation framework that constructs collective representations from individual personas, enabling richer group interaction modeling while preserving behavioral signals and privacy.
Contribution
It presents Synonymix, a novel pipeline for creating unified group personas from multiple individual stories using graph-based abstraction and merging.
Findings
Behavioral signals are preserved beyond demographic baselines (p<0.001, r=0.59).
Synthetic agents demonstrate privacy guarantees with max source contribution <13%.
The approach enables exploration of group-level interaction modalities.
Abstract
Generative agent simulations operate at two scales: individual personas for character interaction, and population models for collective behavior analysis and intervention testing. We propose a third scale: meso-level simulation - interaction with group-level representations that retain grounding in rich individual experience. To enable this, we present Synonymix, a pipeline that constructs a "unigraph" from multiple life story personas via graph-based abstraction and merging, producing a queryable collective representation that can be explored for sensemaking or sampled for synthetic persona generation. Evaluating synthetic agents on General Social Survey items, we demonstrate behavioral signal preservation beyond demographic baselines (p<0.001, r=0.59) with demonstrable privacy guarantee (max source contribution <13%). We invite discussion on interaction modalities enabled by…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
