AlignDiff: Exploiting Model-Intrinsic Information for Better Preference Data Selection

• URL: http://arxiv.org/abs/2609.05899v1
• Date: Sat, 05 Sep 2026 05:51:23 GMT
• Title: AlignDiff: Exploiting Model-Intrinsic Information for Better Preference Data Selection
• Abstract summary: We propose AlignDiff, a preference data filtering framework driven by intrinsic model signals.<n>AlpacaEval 2.0, Arena-Hard, and MT-Bench benchmarks are evaluated.<n>We conduct comprehensive ablation studies to validate the effectiveness of AlignDiff.
• Score: 53.61691036434302
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Aligning large language models with human preferences remains a challenge, primarily due to the critical role of preference data quality in effective alignment. Existing datasets are frequently plagued by inherent noise and distribution shifts, which inherently limit model performance. To bridge this gap, we propose AlignDiff, a preference data filtering framework driven by intrinsic model signals. AlignDiff first identifies samples with clear preferences using both positive and inverse signals, then prioritizes the more challenging samples based on the average negative log-likelihood gap, encouraging the model to learn richer information from them. AlignDiff is evaluated on two widely used model families (LLaMA and Qwen) and three benchmarks widely adopted in the alignment community (AlpacaEval 2.0, Arena-Hard, and MT-Bench). Across all settings, it consistently outperforms seven strong baselines. We conduct comprehensive ablation studies to validate the effectiveness of AlignDiff, and further show that difficulty-based curriculum learning improves model performance.

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)
• Large Language Model for Discrete Optimization Problems: Evaluation and Step-by-step Reasoning [14.271411751541871]
  This work investigated the capabilities of different models, including the Llama-3 series of models and CHATGPT, with different forms of expression in solving discrete optimization problems by testing natural language datasets.<n>It aimed to (1) provide an overview of LLMs' ability in large-scale problems, (2) offer suggestions to those who want to solve discrete optimization problems automatically, and (3) regard the performance as a benchmark for future research.
  arXiv  Detail & Related papers  (2026-03-08T17:02:44Z)
• Towards Understanding Valuable Preference Data for Large Language Model Alignment [85.38864561060088]
  Large language model (LLM) alignment is typically achieved through learning from human preference comparisons.<n>We assess data quality through individual influence on validation data using our newly proposed truncated influence function (TIF)<n>To this end, we combine them to offset their diverse error sources, resulting in a simple yet effective data selection rule.
  arXiv  Detail & Related papers  (2025-10-15T06:57:55Z)
• Anyprefer: An Agentic Framework for Preference Data Synthesis [62.3856754548222]
  We propose Anyprefer, a framework designed to synthesize high-quality preference data for aligning the target model.<n> external tools are introduced to assist the judge model in accurately rewarding the target model's responses.<n>The synthesized data is compiled into a new preference dataset, Anyprefer-V1, consisting of 58K high-quality preference pairs.
  arXiv  Detail & Related papers  (2025-04-27T15:21:59Z)
• DONOD: Efficient and Generalizable Instruction Fine-Tuning for LLMs via Model-Intrinsic Dataset Pruning [22.704995231753397]
  Ad-hoc instruction fine-tuning of large language models (LLMs) is widely adopted for domain-specific adaptation.<n>We propose DONOD, a lightweight model-intrinsic data pruning method.<n>By filtering out 70% of the whole dataset, we improve target-domain accuracy by 14.90% and cross-domain accuracy by 5.67%.
  arXiv  Detail & Related papers  (2025-04-21T02:25:03Z)
• Optimizing LLMs with Direct Preferences: A Data Efficiency Perspective [4.548047308860141]
  This study investigates the impact of different type of preference data on model performance. It aims to reduce their dependency on extensive amounts of preference data, which is expensive to collect.
  arXiv  Detail & Related papers  (2024-10-22T00:11:41Z)
• 3DS: Medical Domain Adaptation of LLMs via Decomposed Difficulty-based Data Selection [27.922627457625477]
  Large Language Models excel in general tasks but struggle in specialized domains like healthcare.<n>We propose a two-stage model-centric data selection framework, De Difficulty Data Selection (3DS)<n>Our experiments on real-world healthcare datasets demonstrate the superiority of 3DS over exisiting methods in accuracy by over 5.29%.
  arXiv  Detail & Related papers  (2024-10-13T02:29:00Z)
• Spread Preference Annotation: Direct Preference Judgment for Efficient LLM Alignment [72.99676237703099]
  We propose a new framework that boosts the alignment of large language models with human preferences.<n>Our key idea is leveraging the human prior knowledge within the small (seed) data.<n>We introduce a noise-aware preference learning algorithm to mitigate the risk of low quality within generated preference data.
  arXiv  Detail & Related papers  (2024-06-06T18:01:02Z)
• Secrets of RLHF in Large Language Models Part II: Reward Modeling [134.97964938009588]
  We introduce a series of novel methods to mitigate the influence of incorrect and ambiguous preferences in the dataset. We also introduce contrastive learning to enhance the ability of reward models to distinguish between chosen and rejected responses.
  arXiv  Detail & Related papers  (2024-01-11T17:56:59Z)
• Decomposed Adversarial Learned Inference [118.27187231452852]
  We propose a novel approach, Decomposed Adversarial Learned Inference (DALI) DALI explicitly matches prior and conditional distributions in both data and code spaces. We validate the effectiveness of DALI on the MNIST, CIFAR-10, and CelebA datasets.
  arXiv  Detail & Related papers  (2020-04-21T20:00:35Z)

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.