# QA-LIGN: Aligning LLMs through Constitutionally Decomposed QA

arXiv: https://arxiv.org/abs/2506.08123 · HTML: https://mlsanity.com/paper/2506.08123/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- Placed in LLM preference optimization methods, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 46 of its 62 references that are in the map.
- First posted on arXiv 9 Jun 2025.

## Placed in

- LLM alignment / RLHF / preference optimisation / [LLM preference optimization methods](https://mlsanity.com/alignment/llm-preference-optimization-methods/)

## Builds on (most cited first, 30 of 46)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters](https://mlsanity.com/paper/2408.03314/) (2024)
- [CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge](https://mlsanity.com/paper/1811.00937/) (2018)
- [Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them](https://mlsanity.com/paper/2210.09261/) (2022)
- [HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal](https://mlsanity.com/paper/2402.04249/) (2024)
- [ZeRO: Memory Optimizations Toward Training Trillion Parameter Models](https://mlsanity.com/paper/1910.02054/) (2019)
- [LIMA: Less Is More for Alignment](https://mlsanity.com/paper/2305.11206/) (2023)
- [Red Teaming Language Models with Language Models](https://mlsanity.com/paper/2202.03286/) (2022)
- [ChatGPT Outperforms Crowd-Workers for Text-Annotation Tasks](https://mlsanity.com/paper/2303.15056/) (2023)
- [Universal Adversarial Triggers for Attacking and Analyzing NLP](https://mlsanity.com/paper/1908.07125/) (2019)
- [RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback](https://mlsanity.com/paper/2309.00267/) (2023)
- [Improving alignment of dialogue agents via targeted human judgements](https://mlsanity.com/paper/2209.14375/) (2022)
- [Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation](https://mlsanity.com/paper/2310.06987/) (2023)
- [ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detection](https://mlsanity.com/paper/2203.09509/) (2022)
- [Fine-Grained Human Feedback Gives Better Rewards for Language Model Training](https://mlsanity.com/paper/2306.01693/) (2023)
- [Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRs](https://mlsanity.com/paper/2503.01307/) (2025)
- [Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discovery](https://mlsanity.com/paper/2302.03668/) (2023)
- [Skywork-Reward: Bag of Tricks for Reward Modeling in LLMs](https://mlsanity.com/paper/2410.18451/) (2024)
- [Principle-Driven Self-Alignment of Language Models from Scratch with Minimal Human Supervision](https://mlsanity.com/paper/2305.03047/) (2023)

## Built on by (most cited first, 28 of 28)

- [Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domains](https://mlsanity.com/paper/2507.17746/) (2025)
- [A Survey of Reinforcement Learning for Large Reasoning Models](https://mlsanity.com/paper/2509.08827/) (2025)
- [Breaking the Exploration Bottleneck: Rubric-Scaffolded Reinforcement Learning for General LLM Reasoning](https://mlsanity.com/paper/2508.16949/) (2025)
- [Compute as Teacher: Turning Inference Compute Into Reference-Free Supervision](https://mlsanity.com/paper/2509.14234/) (2025)
- [InfiMed-ORBIT: Aligning LLMs on Open-Ended Complex Tasks via Rubric-Based Incremental Training](https://mlsanity.com/paper/2510.15859/) (2025)
- [RubricRAG: Towards Interpretable and Reliable LLM Evaluation via Domain Knowledge Retrieval for Rubric Generation](https://mlsanity.com/paper/2603.20882/) (2026)
- [Self-Preference Bias in Rubric-Based Evaluation of Large Language Models](https://mlsanity.com/paper/2604.06996/) (2026)
- [PaTaRM: Bridging Pairwise and Pointwise Signals via Preference-Aware Task-Adaptive Reward Modeling](https://mlsanity.com/paper/2510.24235/) (2025)
- [Am I More Pointwise or Pairwise? Revealing Position Bias in Rubric-Based LLM-as-a-Judge](https://mlsanity.com/paper/2602.02219/) (2026)
- [AutoChecklist: Composable Pipelines for Checklist Generation and Scoring with LLM-as-a-Judge](https://mlsanity.com/paper/2603.07019/) (2026)
- [Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text](https://mlsanity.com/paper/2604.20051/) (2026)
- [JudgmentBench: Comparing Rubric and Preference Evaluation for Quality Assessment](https://mlsanity.com/paper/2605.25240/) (2026)
- [CriPO: Enhancing Rubric-based RL via Self-Distillation](https://mlsanity.com/paper/2607.18082/) (2026)
- [Multidimensional Rubric-oriented Reward Model Learning via Geometric Projection Reference Constraints](https://mlsanity.com/paper/2511.16139/) (2025)
- [SPARD: Self-Paced Curriculum for RL Alignment via Integrating Reward Dynamics and Data Utility](https://mlsanity.com/paper/2604.07837/) (2026)
- [Asking What Matters: Reward-Driven Clarification for Software Engineering Tasks](https://mlsanity.com/paper/2604.14624/) (2026)
- [From Holistic Evaluation to Structured Criteria: Rubrics Across the Evolving LLM Landscape](https://mlsanity.com/paper/2606.08625/) (2026)
- [RECAP: Transparent Inference-Time Emotion Alignment for Medical Dialogue Systems](https://mlsanity.com/paper/2509.10746/) (2025)
- [A Survey on Rubric-Guided Reinforcement Learning for Language Models](https://mlsanity.com/paper/2608.27505/) (2026)
- [Reflect: Transparent Principle-Guided Reasoning for Constitutional Alignment at Scale](https://mlsanity.com/paper/2601.18730/) (2026)
- [Curing Miracle Steps in LLM Mathematical Reasoning with Rubric Rewards](https://mlsanity.com/paper/2510.07774/) (2025)
- [When Rubrics Fail: Error Enumeration as Reward in Reference-Free RL Post-Training for Virtual Try-On](https://mlsanity.com/paper/2603.05659/) (2026)
- [Vocabulary Dropout for Curriculum Diversity in LLM Co-Evolution](https://mlsanity.com/paper/2604.03472/) (2026)
- [Grounded Checklist Partial Credit for Agent Skill Trajectories](https://mlsanity.com/paper/2608.27487/) (2026)
- [Evaluating Medical LLMs by Levels of Autonomy: A Survey Moving from Benchmarks to Applications](https://mlsanity.com/paper/2510.17764/) (2025)
- [Discovering Implicit Large Language Model Alignment Objectives](https://mlsanity.com/paper/2602.15338/) (2026)
- [Decomposer: Learning to Decompile Symbolic Music to Programs](https://mlsanity.com/paper/2607.01849/) (2026)
- [From Constitutions to Control: Interpretable Rewards for Aligning Language Models](https://mlsanity.com/paper/2609.33086/) (2026)

## Abstract (arXiv)

Alignment of large language models (LLMs) with principles like helpfulness, honesty, and harmlessness typically relies on scalar rewards that obscure which objectives drive the training signal. We introduce QA-LIGN, which decomposes monolithic rewards into interpretable principle-specific evaluations through structured natural language programs. Models learn through a draft, critique, and revise pipeline, where symbolic evaluation against the rubrics provides transparent feedback for both initial and revised responses during GRPO training. Applied to uncensored Llama-3.1-8B-Instruct, QA-LIGN reduces attack success rates by up to 68.7% while maintaining a 0.67% false refusal rate, achieving Pareto optimal safety-helpfulness performance and outperforming both DPO and GRPO with state-of-the-art reward models given equivalent training. These results demonstrate that making reward signals interpretable and modular improves alignment effectiveness, suggesting transparency enhances LLM safety.