# Self-supervised Attribute-aware Dynamic Preference Ranking Alignment

arXiv: https://arxiv.org/abs/2502.12189 · HTML: https://mlsanity.com/paper/2502.12189/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in LLM preference optimization methods, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 27 of its 60 references that are in the map.
- First posted on arXiv 15 Feb 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, 27 of 27)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (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)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!](https://mlsanity.com/paper/2310.03693/) (2023)
- [ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools](https://mlsanity.com/paper/2406.12793/) (2024)
- [A General Language Assistant as a Laboratory for Alignment](https://mlsanity.com/paper/2112.00861/) (2021)
- [Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2307.15217/) (2023)
- [CogVLM: Visual Expert for Pretrained Language Models](https://mlsanity.com/paper/2311.03079/) (2023)
- [StarCoder 2 and The Stack v2: The Next Generation](https://mlsanity.com/paper/2402.19173/) (2024)
- [Zephyr: Direct Distillation of LM Alignment](https://mlsanity.com/paper/2310.16944/) (2023)
- [UltraFeedback: Boosting Language Models with Scaled AI Feedback](https://mlsanity.com/paper/2310.01377/) (2023)
- [LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders](https://mlsanity.com/paper/2404.05961/) (2024)
- [SLiC-HF: Sequence Likelihood Calibration with Human Feedback](https://mlsanity.com/paper/2305.10425/) (2023)
- [Statistical Rejection Sampling Improves Preference Optimization](https://mlsanity.com/paper/2309.06657/) (2023)
- [KTO: Model Alignment as Prospect Theoretic Optimization](https://mlsanity.com/paper/2402.01306/) (2024)
- [PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human Preference](https://mlsanity.com/paper/2406.15513/) (2024)
- [Arithmetic Control of LLMs for Diverse User Preferences: Directional Preference Alignment with Multi-Objective Rewards](https://mlsanity.com/paper/2402.18571/) (2024)
- [Language Models are Homer Simpson! Safety Re-Alignment of Fine-tuned Language Models through Task Arithmetic](https://mlsanity.com/paper/2402.11746/) (2024)
- [CodeBERTScore: Evaluating Code Generation with Pretrained Models of Code](https://mlsanity.com/paper/2302.05527/) (2023)
- [LiPO: Listwise Preference Optimization through Learning-to-Rank](https://mlsanity.com/paper/2402.01878/) (2024)
- [Learning or Self-aligning? Rethinking Instruction Fine-tuning](https://mlsanity.com/paper/2402.18243/) (2024)
- [Curry-DPO: Enhancing Alignment using Curriculum Learning & Ranked Preferences](https://mlsanity.com/paper/2403.07230/) (2024)
- [Enhancing Dialogue State Tracking Models through LLM-backed User-Agents Simulation](https://mlsanity.com/paper/2405.13037/) (2024)
- [HOLMES: Hyper-Relational Knowledge Graphs for Multi-hop Question Answering using LLMs](https://mlsanity.com/paper/2406.06027/) (2024)
- [LIRE: listwise reward enhancement for preference alignment](https://mlsanity.com/paper/2405.13516/) (2024)

## Abstract (arXiv)

Reinforcement Learning from Human Feedback and its variants excel in aligning with human intentions to generate helpful, harmless, and honest responses. However, most of them rely on costly human-annotated pairwise comparisons for supervised alignment, which is not suitable for list-level scenarios, such as community question answering. Additionally, human preferences are influenced by multiple intrinsic factors in responses, leading to decision-making inconsistencies. Therefore, we propose Self-supervised Attribute-aware dynamic preference ranking, called shortname.  It quantifies preference differences between responses based on Attribute-Perceptual Distance Factors (APDF) and dynamically determines the list-wise alignment order. Furthermore, it achieves fine-grained preference difference learning and enables precise alignment with the optimal one. We specifically constructed a challenging code preference dataset named StaCoCoQA, and introduced more cost-effective and scalable preference evaluation metrics: PrefHit and PrefRecall. Extensive experimental results show that SeAdpra exhibits superior performance and generalizability on both StaCoCoQA and preference datasets from eight popular domains.