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

DevFeed: [From Preferences to Principles: Rubric-Based Alignment for Grounded Knowledge Answers](<https://devfeed.tech/articles/from-preferences-to-principles-rubric-based-alignment-for-grounded-knowledge-answers-6734.md>)

Original publisher: [Read original article](<https://machinelearning.apple.com/research/rubric-based-alignment>)

Published: 2026-08-27T00:00:00Z

Content type: article

Language: en

Sources: [Apple Machine Learning Research](<https://devfeed.tech/sources/apple-machine-learning-research.md>)

Topics: [Large Language Model](<https://devfeed.tech/topics/llm.md>), [LLM evaluation / benchmarking](<https://devfeed.tech/topics/llm-evaluation-benchmarking.md>), [Natural language processing](<https://devfeed.tech/topics/nlp.md>), [datasets](<https://devfeed.tech/topics/datasets.md>)

Tags: [datasets](<https://devfeed.tech/tags/datasets.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [models](<https://devfeed.tech/tags/models.md>), [post-training](<https://devfeed.tech/tags/post-training.md>), [research](<https://devfeed.tech/tags/research.md>), [responses](<https://devfeed.tech/tags/responses.md>), [search](<https://devfeed.tech/tags/search.md>)

## AI overview

The article introduces a rubric-based reward framework for grounded open-domain question answering. It generates query-specific rubrics from retrieved evidence and decomposes them into quality dimensions for fine-grained post-training supervision. The method improves composition, grounding, and instruction-following results over the stated baselines and evaluation datasets.

## Source excerpt

Designing effective reward signals for open-domain question answering is challenging because high-quality responses must simultaneously satisfy multiple aspects of answer quality that are difficult to capture with a holistic scalar objective. We introduce a rubric-based reward framework that generates query-specific rubrics grounded in retrieved evidence and decomposed into multiple quality dimensions, providing fine-grained supervision during post-training. Averaged across three evaluation axes (composition, grounding, and instruction-following), our approach improves over the...