MuseCritic is introduced, a semi-scalar reward model that generates a natural-language critique covering five aesthetic dimensions and uses it as an intermediate representation to predict continuous reward scores, showing that critique-conditioned reward modeling reduces scoring error and provides an effective optimiza...
Jiabao Zhuang, Changhao Jiang, Hanchen Wang et al.· 0 citations
When training data are limited, increasing parameter count is not the only way to improve language-model performance. A small parameter set, when repeatedly applied, can also deliver comparable performance. We study Looped GPT-BERT in the BabyLM 2026 Strict-small setting, combining GPT-BERT's masked next-token and caus...
Ting-Shuo Fan, Hong-Tao Mu, Tian-Yun Zhou et al.· 0 citations
A critique-in-the-loop self-improvement method that incorporates critique-based supervision into the actor’s self-training process and improves the actor’s exploration efficiency and solution diversity, especially on challenging queries, leading to a stronger actor model.
Zhi-Heng Xi, Dingwen Yang, Jixuan Huang et al.· Proceedings of the Thirty-Fi...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
