Nov 5, 2024 · Artificial Intelligence

Bilibili's In-House Role-Playing Large Language Model: Architecture, Training Stages, Evaluation, and Demonstrations

Bilibili’s in‑house role‑playing large language model, built on the Index architecture and refined through pre‑training, supervised fine‑tuning, and preference optimization (PPO and DPO), achieved top scores on the Chinese CharacterEval benchmark, surpassing rivals while incorporating safety alignment and showcasing consistent, personality‑driven dialogue examples.

Content SafetyPreference OptimizationSupervised Fine‑Tuning

0 likes · 13 min read

Bilibili's In-House Role-Playing Large Language Model: Architecture, Training Stages, Evaluation, and Demonstrations