# REWARD CONSISTENCY: Improving Multi-Objective Alignment from a Data-Centric Perspective

arXiv: https://arxiv.org/abs/2504.11337 · HTML: https://mlsanity.com/paper/2504.11337/

## Key facts

- Cited by 5 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 28 of its 39 references that are in the map.
- First posted on arXiv 15 Apr 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, 28 of 28)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [LIMA: Less Is More for Alignment](https://mlsanity.com/paper/2305.11206/) (2023)
- [SimPO: Simple Preference Optimization with a Reference-Free Reward](https://mlsanity.com/paper/2405.14734/) (2024)
- [A General Theoretical Paradigm to Understand Learning from Human Preferences](https://mlsanity.com/paper/2310.12036/) (2023)
- [Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2307.15217/) (2023)
- [Safe RLHF: Safe Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2310.12773/) (2023)
- [ORPO: Monolithic Preference Optimization without Reference Model](https://mlsanity.com/paper/2403.07691/) (2024)
- [LESS: Selecting Influential Data for Targeted Instruction Tuning](https://mlsanity.com/paper/2402.04333/) (2024)
- [Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs](https://mlsanity.com/paper/2406.18629/) (2024)
- [Rewarded soups: towards Pareto-optimal alignment by interpolating weights fine-tuned on diverse rewards](https://mlsanity.com/paper/2306.04488/) (2023)
- [Rewards-in-Context: Multi-objective Alignment of Foundation Models with Dynamic Preference Adjustment](https://mlsanity.com/paper/2402.10207/) (2024)
- [Beyond One-Preference-Fits-All Alignment: Multi-Objective Direct Preference Optimization](https://mlsanity.com/paper/2310.03708/) (2023)
- [SteerLM: Attribute Conditioned SFT as an (User-Steerable) Alternative to RLHF](https://mlsanity.com/paper/2310.05344/) (2023)
- [Understanding the performance gap between online and offline alignment algorithms](https://mlsanity.com/paper/2405.08448/) (2024)
- [Controllable Preference Optimization: Toward Controllable Multi-Objective Alignment](https://mlsanity.com/paper/2402.19085/) (2024)
- [Panacea: Pareto Alignment via Preference Adaptation for LLMs](https://mlsanity.com/paper/2402.02030/) (2024)
- [Uncovering Safety Risks of Large Language Models through Concept Activation Vector](https://mlsanity.com/paper/2404.12038/) (2024)
- [Bootstrapping Language Models with DPO Implicit Rewards](https://mlsanity.com/paper/2406.09760/) (2024)
- [Curry-DPO: Enhancing Alignment using Curriculum Learning & Ranked Preferences](https://mlsanity.com/paper/2403.07230/) (2024)
- [On the Limited Generalization Capability of the Implicit Reward Model Induced by Direct Preference Optimization](https://mlsanity.com/paper/2409.03650/) (2024)
- [SPO: Multi-Dimensional Preference Sequential Alignment With Implicit Reward Modeling](https://mlsanity.com/paper/2405.12739/) (2024)
- [SeRA: Self-Reviewing and Alignment of Large Language Models using Implicit Reward Margins](https://mlsanity.com/paper/2410.09362/) (2024)

## Built on by (most cited first, 5 of 5)

- [OrthAlign: Orthogonal Subspace Decomposition for Non-Interfering Multi-Objective Alignment](https://mlsanity.com/paper/2509.24610/) (2025)
- [Explaining and Breaking the Safety-Helpfulness Ceiling via Preference Dimensional Expansion](https://mlsanity.com/paper/2605.11679/) (2026)
- [STAGE: Controlled Objective Admission for Multi-Preference LLM Alignment](https://mlsanity.com/paper/2608.16553/) (2026)
- [AR-MAP: Are Autoregressive Large Language Models Implicit Teachers for Diffusion Large Language Models?](https://mlsanity.com/paper/2602.02178/) (2026)
- [Multi-Objective Exploration and Preference Optimization via Mutual Information](https://mlsanity.com/paper/2607.01392/) (2026)

## Abstract (arXiv)

Multi-objective preference alignment in language models often encounters a challenging trade-off: optimizing for one human preference (e.g., helpfulness) frequently compromises others (e.g., harmlessness) due to the inherent conflicts between competing objectives. While prior work mainly focuses on algorithmic solutions, we explore a novel data-driven approach to uncover the types of data that can effectively mitigate these conflicts. Specifically, we propose the concept of Reward Consistency (RC), which identifies samples that align with multiple preference objectives, thereby reducing conflicts during training. Through gradient-based analysis, we demonstrate that RC-compliant samples inherently constrain performance degradation during multi-objective optimization. Building on these insights, we further develop Reward Consistency Sampling, a framework that automatically constructs preference datasets that effectively mitigate conflicts during multi-objective alignment. Our generated data achieves an average improvement of 13.37% in both the harmless rate and helpfulness win rate when optimizing harmlessness and helpfulness, and can consistently resolve conflicts in varying multi-objective scenarios.