Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Hierarchical Multi-Persona Induction from User Behavioral Logs: Learning Evidence-Grounded and Truthful Personas

About

Behavioral logs provide rich signals for user modeling, but are noisy and interleaved across diverse intents. Recent work uses LLMs to generate interpretable natural-language personas from user logs, yet evaluation often emphasizes downstream utility, providing limited assurance of persona quality itself. We propose a hierarchical framework that aggregates user actions into intent memories and induces multiple evidence-grounded personas by clustering and labeling these memories. We formulate persona induction as an optimization problem over persona quality-captured by cluster cohesion, persona-evidence alignment, and persona truthfulness-and train the persona model using a groupwise extension of Direct Preference Optimization (DPO). Experiments on a large-scale service log and two public datasets show that our method induces more coherent, evidence-grounded, and trustworthy personas, while also improving future interaction prediction.

Nayoung Choi, Haeyu Jeong, Changbong Kim, Hongjun Lim, Jinho D. Choi• 2026

Related benchmarks

TaskDatasetResultRank
Future Interaction PredictionSrv (test)
Hit Rate @ 1031.39
7
Future Interaction PredictionMerRec (test)
Hit Rate@1058.65
7
Future Interaction PredictionAOL (test)
Hit Rate @1040.18
7
Persona InductionSrv (test)
Coherence0.455
7
Persona InductionMerRec (test)
Coherence0.674
7
Persona InductionAOL (test)
Coherence71.8
7
Showing 6 of 6 rows

Other info

Follow for update