AdvancedIF: Rubric-Based Benchmarking and Reinforcement Learning for Advancing LLM Instruction Following
About
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 (we will release this benchmark soon), 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 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.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Instruction Following | IFEval | -- | 836 | |
| Instruction Following | AdvancedIF | Accuracy47.29 | 102 | |
| Instruction Following | FollowBench | -- | 85 | |
| Reward Modeling | HelpSteer 3 | Accuracy67.7 | 62 | |
| Reward Modeling | RewardBench Chat | Accuracy89.7 | 42 | |
| Reward Modeling | RM-Bench Chat | Accuracy64.8 | 42 | |
| Reward Modeling | RewardBench 2 | Precise IF Score42.3 | 41 | |
| Instruction Following | MulDimIF | Score74.38 | 36 | |
| Instruction Following Evaluation | PPE-IFEval | Score75.8 | 24 | |
| Instruction Following Evaluation | IFBench | Score69.8 | 23 |