@inproceedings{he-etal-2026-advancedif,
    title = "{A}dvanced{IF}: Rubric-Based Benchmarking and Reinforcement Learning for Advancing {LLM} Instruction Following",
    author = "He, Yun  and
      Li, Wenzhe  and
      Zhang, Hejia  and
      Li, Songlin  and
      Mandyam, Karishma  and
      Khosla, Sopan  and
      Xiong, Yuanhao  and
      Wang, Nanshu  and
      Peng, Xiaoliang  and
      Li, Beibin  and
      Bi, Shengjie  and
      Patil, Shishir G  and
      Qi, Qi  and
      Feng, Shengyu  and
      Katz-Samuels, Julian  and
      Pang, Richard Yuanzhe  and
      Gonugondla, Sujan Kumar  and
      Lang, Hunter  and
      Yu, Yue  and
      Qian, Yundi  and
      Fazel-Zarandi, Maryam  and
      Yu, Licheng  and
      Benhalloum, Amine  and
      Awadalla, Hany Hassan  and
      Faruqui, Manaal",
    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.820/",
    pages = "18003--18022",
    ISBN = "979-8-89176-390-6",
    abstract = "Recent progress in large language models (LLMs) has led to impressive performance on a range of tasks, yet advanced instruction following (IF){---}especially for complex, multi-turn, and system-prompted instructions{---}remains a significant challenge. Rigorous evaluation and effective training for such capabilities are hindered by the lack of high-quality, human-annotated benchmarks and reliable, interpretable reward signals. In this work, we introduce AdvancedIF, a comprehensive benchmark featuring over 1,600 prompts and expert-curated rubrics that assess LLMs' ability to follow complex, multi-turn, and system-level instructions. We also open-source the evaluation script of AdvancedIF. We further propose RIFL (Rubric-based Instruction-Following Learning), a novel post-training pipeline that leverages rubric generation, a finetuned rubric verifier, and reward shaping to enable effective reinforcement learning for instruction following. Extensive experiments demonstrate that RIFL substantially improves the instruction-following abilities of LLMs, achieving a 6.7{\%} absolute gain on AdvancedIF and strong results on public benchmarks. Our ablation studies confirm the effectiveness of each component in RIFL. This work establishes rubrics as a powerful tool for both training and evaluating advanced IF in LLMs, paving the way for more capable and reliable AI systems."
}