This work introduces STAR, a framework for studying how closely the dispositions expressed by LLMs align with those of humans, and finds that LLM recommendations are substantially less diverse than human choices, both within individual models and even across models from different providers.
Amir Taubenfeld, Zorik Gekhman, Lior Nezry et al.· arXiv.org· 7 citations
This work introduces Fuse, a multi-agent simulation framework for studying user-mediated social reasoning, and applies Fuse to 12 LLMs and demonstrates its analytical utility by systematically isolating key factors.
Amir Taubenfeld, Zorik Gekhman, Avigail Grinstein-Dabush et al.· 2 citations
This work proposes a self-distillation-based SFT method that facilitates effective factual learning while minimizing hallucinations w.r.t.~pre-existing knowledge by regularizing output-distribution drift and investigates the mechanism, contrasting capacity limitations, behavior cloning, and localized interference.
Guy Kaplan, Zorik Gekhman, Zhen Zhu et al.· arXiv.org· 5 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.