Dokumentdetails
ID
oai:arXiv.org:2407.17387
Thema
Computer Science - Computation and...Autor
Castricato, Louis Lile, Nathan Rafailov, Rafael Fränken, Jan-Philipp Finn, ChelseaKategorie
Computer Science
Jahr
2024
Auflistungsdatum
31.07.2024
Schlüsselwörter
diverse user persona datasetZusammenfassung
The rapid advancement of language models (LMs) necessitates robust alignment with diverse user values.
However, current preference optimization approaches often fail to capture the plurality of user opinions, instead reinforcing majority viewpoints and marginalizing minority perspectives.
We introduce PERSONA, a reproducible test bed designed to evaluate and improve pluralistic alignment of LMs.
We procedurally generate diverse user profiles from US census data, resulting in 1,586 synthetic personas with varied demographic and idiosyncratic attributes.
We then generate a large-scale evaluation dataset containing 3,868 prompts and 317,200 feedback pairs obtained from our synthetic personas.
Leveraging this dataset, we systematically evaluate LM capabilities in role-playing diverse users, verified through human judges, and the establishment of both a benchmark, PERSONA Bench, for pluralistic alignment approaches as well as an extensive dataset to create new and future benchmarks.
The full dataset and benchmarks are available here: https://www.synthlabs.ai/research/persona.
Castricato, Louis,Lile, Nathan,Rafailov, Rafael,Fränken, Jan-Philipp,Finn, Chelsea, 2024, PERSONA: A Reproducible Testbed for Pluralistic Alignment
MELAS: Phenotype Classification into Classic-versus-Atypical Presentations
presentations mitochondrial strokelike patients variability phenotype clinical melas
