From Preferences to Principles: Rubric-Based Alignment for Grounded Knowledge Answers

arXiv:2608.23812 · cs.CL · Submitted 2026-08-24 · Read on arXiv

cs.CL

Submitted: 2026-08-24

Updated: 2026-08-24

Code: https://github.com/apple/ml-complex-qa-queries

Terminology

• Grounding — 35× in this paper · explained in 3 episodes
• Accuracy — 13× in this paper · explained in 1 episode
• Benchmark — 12× in this paper · explained in 2 episodes
• Reinforcement Learning — 10× in this paper · explained in 4 episodes
• Alignment — 8× in this paper · explained in 1 episode
• Ablation — 4× in this paper · explained in 1 episode
• Consistency — 4× in this paper · explained in 3 episodes
• LLM-as-a-Judge — 4× in this paper · explained in 3 episodes
• RAG — 4× in this paper · explained in 3 episodes
• Redundancy — 4× in this paper · explained in 2 episodes
• Adam — 3× in this paper · explained in 2 episodes
• Aggregation — 3× in this paper · explained in 1 episode
• GRPO — 3× in this paper · explained in 6 episodes
• Actionability — 2× in this paper · explained in 3 episodes
• Core — 2× in this paper · explained in 2 episodes
• Generalization — 2× in this paper · explained in 13 episodes
• Hallucination — 2× in this paper · explained in 4 episodes
• Reward Hacking — 2× in this paper · explained in 8 episodes
• Robustness — 2× in this paper · explained in 5 episodes
• Benchmarking — 1× in this paper · explained in 4 episodes
• Commentary — 1× in this paper · explained in 2 episodes
• Deep Reinforcement Learning — 1× in this paper · explained in 2 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Generative Model — 1× in this paper · explained in 2 episodes
• Group Relative Policy Optimization — 1× in this paper
• Group Relative Policy Optimization (GRPO) — 1× in this paper · explained in 5 episodes
• Interpretability — 1× in this paper · explained in 15 episodes
• LLM judge — 1× in this paper · explained in 2 episodes
• Multi-hop Reasoning — 1× in this paper · explained in 3 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Reinforcement Learning (RL) — 1× in this paper · explained in 25 episodes
• Retrieval-Augmented Generation (RAG) — 1× in this paper · explained in 16 episodes
• Scaling Laws — 1× in this paper · explained in 4 episodes
• Sycophancy — 1× in this paper · explained in 4 episodes
• Verifiable Rewards — 1× in this paper · explained in 2 episodes
• Verifier — 1× in this paper · explained in 2 episodes

Sources

• RAGBench: Explainable Benchmark for Retrieval-Augmented Generation Systems
• Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domains
• AdvancedIF: Rubric-Based Benchmarking and Reinforcement Learning for Advancing LLM Instruction Following
• HAGRID: A Human-LLM Collaborative Dataset for Generative Information-Seeking with Attribution
• MS MARCO: A Human Generated MAchine Reading COmprehension Dataset
• Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback
• Holistic Evaluation of Language Models
• The FACTS Leaderboard: A Comprehensive Benchmark for Large Language Model Factuality
• OpenRubrics: Towards Scalable Synthetic Rubric Generation for Reward Modeling and LLM Alignment
• Towards Understanding Sycophancy in Language Models
• A Long Way to Go: Investigating Length Correlations in RLHF
• ExpertQA: Expert-Curated Questions and Attributed Answers
• Defining and Characterizing Reward Hacking
• Search Arena: Analyzing Search-Augmented LLMs
• Checklists Are Better Than Reward Models For Aligning Language Models
• GPT-4o System Card
• HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering
• OpenGenAlign: A Preference Dataset and Benchmark for Trustworthy Reward Modeling in Open-Ended, Long-Context Generation
• Disentangling Length from Quality in Direct Preference Optimization
• Chasing the Tail: Effective Rubric-based Reward Modeling for Large Language Model Post-Training

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering