@inproceedings{zhang-2026-arf,
    title = "{ARF}-{RLHF}: Adaptive Reward-Following for {RLHF} through Emotion-Driven Self-Supervision and Trace-Biased Dynamic Optimization",
    author = "Zhang, Yuxuan",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.1637/",
    pages = "35406--35425",
    ISBN = "979-8-89176-390-6",
    abstract = "Current RLHF methods such as PPO and DPO typically reduce human preferences to binary labels, which are costly to obtain and too coarse to reflect individual variation. We observe that expressions of satisfaction and dissatisfaction follow stable linguistic patterns across users, indicating that more informative supervisory signals can be extracted from free-form feedback. Building on this insight, we introduce Adaptive Reward-Following (ARF), which converts natural feedback into continuous preference trajectories and optimizes them using the novel TraceBias algorithm. Across diverse LLMs and preference domains, ARF consistently outperforms PPO and DPO, improving alignment by up to 7.6{\%}. Our results demonstrate that continuous reward modeling provides a scalable path toward personalized and theoretically grounded RLHF."
}