This repository contains the persona adapter models presented in the paper FrameRef: A Framing Dataset and Simulation Testbed for Modeling Bounded Rational Information Health.

All adapters in this repository are LoRA adapters trained on top of the Llama-3.1-8B-Instruct base model using 15k training samples. For each framing dimension (authoritative, consensus, emotional, prestige, and sensationalist), we release three independently trained adapters. The baseline adapters were trained with alpha = 1, while all other adapters were trained with alpha = 0.3.

Within the FrameRef framework, these framing-sensitive agent personas are constructed by fine-tuning language models with framing-conditioned loss attenuation, inducing targeted biases while preserving overall task competence. For full details, see the accompanying paper.

If you use this resource in your projects, please cite the following paper: