Self-supervised Attribute-aware Dynamic Preference Ranking Alignment

• URL: http://arxiv.org/abs/2502.12189v1
• Date: Sat, 15 Feb 2025 08:20:42 GMT
• Title: Self-supervised Attribute-aware Dynamic Preference Ranking Alignment
• Abstract summary: We propose textbfSelf-supervised textbfAttribute-aware textbfdynamic textbfpreference textbfranking, called shortname.<n>It quantifies preference differences between responses based on Attribute-Perceptual Distance Factors (APDF) and dynamically determines the list-wise alignment order.<n>It achieves fine-grained preference difference learning and enables precise alignment with the optimal one.
• Score: 21.572914948747748
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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 \textbf{Se}lf-supervised \textbf{A}ttribute-aware \textbf{d}ynamic \textbf{p}reference \textbf{ra}nking, 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.

Related papers

• Preference Data Selection for Mitigating the Alignment Tax in Large Language Models [52.18310687523229]
  BALIGN is a balanced data selection strategy that mitigates catastrophic forgetting while optimizing alignment efficacy.<n>By aggregating three key data-centric features into a unified composite risk score, BALIGN systematically filters out high-risk preference samples.<n>Experiments on standard human preference datasets demonstrate that BALIGN strongly preserves foundational capabilities without compromising alignment gains.
  arXiv  Detail & Related papers  (2026-08-25T07:58:42Z)
• CriterAlign: Criterion-Centric Rationale Alignment for Code Preference Judging [95.02210956333374]
  We propose a criterion-centric framework that adapts rubric-based judging to pairwise preference evaluation.<n>On BigCodeReward, CriterAlign improves a Qwen2.5-VL-32B monolithic judge from 60.4% to 66.3% accuracy.
  arXiv  Detail & Related papers  (2026-05-19T10:59:19Z)
• Listwise Preference Diffusion Optimization for User Behavior Trajectories Prediction [41.53271688465831]
  We formulate User Behavior Trajectory Prediction (UBTP) as a new task setting that explicitly models long-term user preferences.<n>We introduce Listwise Preference Diffusion Optimization (LPDO), a diffusion-based training framework that directly optimize structured preferences over entire item sequences.<n>To rigorously evaluate multi-step prediction quality, we propose the task-specific metric Sequential Match (SeqMatch), which measures exact trajectory agreement, and adopt Perplexity (PPL), which assesses probabilistic fidelity.
  arXiv  Detail & Related papers  (2025-11-01T12:16:24Z)
• Personalized Recommendations via Active Utility-based Pairwise Sampling [1.704905100460915]
  We propose a utility-based framework that learns preferences from simple and intuitive pairwise comparisons.<n>A central contribution of our work is a novel utility-based active sampling strategy for preference elicitation.
  arXiv  Detail & Related papers  (2025-08-12T19:09:33Z)
• Towards Human-like Preference Profiling in Sequential Recommendation [42.100841285901474]
  RecPO is a preference optimization framework for sequential recommendation.<n>It exploits adaptive reward margins based on inferred preference hierarchies and temporal signals.<n>It mirrors key characteristics of human decision-making: favoring timely satisfaction, maintaining coherent preferences, and exercising discernment under shifting contexts.
  arXiv  Detail & Related papers  (2025-06-02T21:09:29Z)
• In-context Ranking Preference Optimization [48.36442791241395]
  We propose an In-context Ranking Preference Optimization (IRPO) framework to optimize large language models (LLMs) based on ranking lists constructed during inference.<n>We show IRPO outperforms standard DPO approaches in ranking performance, highlighting its effectiveness in aligning LLMs with direct in-context ranking preferences.
  arXiv  Detail & Related papers  (2025-04-21T23:06:12Z)
• AIR: A Systematic Analysis of Annotations, Instructions, and Response Pairs in Preference Dataset [95.45316956434608]
  Preference learning is critical for aligning large language models with human values. Our work shifts preference dataset design from ad hoc scaling to component-aware optimization.
  arXiv  Detail & Related papers  (2025-04-04T17:33:07Z)
• SHAPE : Self-Improved Visual Preference Alignment by Iteratively Generating Holistic Winner [35.843587407696006]
  Large Visual Language Models (LVLMs) increasingly rely on preference alignment to ensure reliability. We present projectname, a self-supervised framework capable of transforming the already abundant supervised text-image pairs into holistic preference triplets.
  arXiv  Detail & Related papers  (2025-03-06T08:33:11Z)
• A Systematic Examination of Preference Learning through the Lens of Instruction-Following [83.71180850955679]
  We use a novel synthetic data generation pipeline to generate 48,000 instruction unique-following prompts.<n>With our synthetic prompts, we use two preference dataset curation methods - rejection sampling (RS) and Monte Carlo Tree Search (MCTS)<n>Experiments reveal that shared prefixes in preference pairs, as generated by MCTS, provide marginal but consistent improvements.<n>High-contrast preference pairs generally outperform low-contrast pairs; however, combining both often yields the best performance.
  arXiv  Detail & Related papers  (2024-12-18T15:38:39Z)
• SWEPO: Simultaneous Weighted Preference Optimization for Group Contrastive Alignment [16.230186347702737]
  We introduce Simultaneous Weighted Preference Optimization (SWEPO), a novel extension of Direct Preference Optimization (DPO)<n>SWEPO accommodate multiple dynamically chosen positive and negative responses for each query.<n>We show that simultaneously considering multiple preferences reduces alignment bias, resulting in more robust alignment.<n> Empirical validation on the UltraFeedback dataset establishes SWEPO as state-of-the-art, with superior performance in downstream evaluations.
  arXiv  Detail & Related papers  (2024-12-05T21:50:22Z)
• Ordinal Preference Optimization: Aligning Human Preferences via NDCG [28.745322441961438]
  We develop an end-to-end preference optimization algorithm by approxing NDCG with a differentiable surrogate loss. OPO outperforms existing pairwise and listwise approaches on evaluation sets and general benchmarks like AlpacaEval.
  arXiv  Detail & Related papers  (2024-10-06T03:49:28Z)
• Adaptive Preference Scaling for Reinforcement Learning with Human Feedback [103.36048042664768]
  Reinforcement learning from human feedback (RLHF) is a prevalent approach to align AI systems with human values. We propose a novel adaptive preference loss, underpinned by distributionally robust optimization (DRO) Our method is versatile and can be readily adapted to various preference optimization frameworks.
  arXiv  Detail & Related papers  (2024-06-04T20:33:22Z)
• Comparing Bad Apples to Good Oranges: Aligning Large Language Models via Joint Preference Optimization [105.3612692153615]
  We propose a new axis based on eliciting preferences jointly over instruction-response pairs.<n>Joint preferences over instruction and response pairs can significantly enhance the alignment of large language models.
  arXiv  Detail & Related papers  (2024-03-31T02:05:40Z)
• Linear Alignment: A Closed-form Solution for Aligning Human Preferences without Tuning and Feedback [70.32795295142648]
  Linear alignment is a novel algorithm that aligns language models with human preferences in one single inference step. Experiments on both general and personalized preference datasets demonstrate that linear alignment significantly enhances the performance and efficiency of LLM alignment.
  arXiv  Detail & Related papers  (2024-01-21T10:46:23Z)
• AlignDiff: Aligning Diverse Human Preferences via Behavior-Customisable Diffusion Model [69.12623428463573]
  AlignDiff is a novel framework to quantify human preferences, covering abstractness, and guide diffusion planning. It can accurately match user-customized behaviors and efficiently switch from one to another. We demonstrate its superior performance on preference matching, switching, and covering compared to other baselines.
  arXiv  Detail & Related papers  (2023-10-03T13:53:08Z)
• SetRank: A Setwise Bayesian Approach for Collaborative Ranking from Implicit Feedback [50.13745601531148]
  We propose a novel setwise Bayesian approach for collaborative ranking, namely SetRank, to accommodate the characteristics of implicit feedback in recommender system. Specifically, SetRank aims at maximizing the posterior probability of novel setwise preference comparisons. We also present the theoretical analysis of SetRank to show that the bound of excess risk can be proportional to $sqrtM/N$.
  arXiv  Detail & Related papers  (2020-02-23T06:40:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.