DAMA: Data- and Model-aware Alignment of Multi-modal LLMs

• URL: http://arxiv.org/abs/2502.01943v2
• Date: Tue, 11 Feb 2025 03:55:29 GMT
• Title: DAMA: Data- and Model-aware Alignment of Multi-modal LLMs
• Authors: Jinda Lu, Junkang Wu, Jinghan Li, Xiaojun Jia, Shuo Wang, YiFan Zhang, Junfeng Fang, Xiang Wang, Xiangnan He,
• Abstract summary: We propose Data- and Model-aware DPO (DAMA) to adjust the optimization process from two key aspects.<n>By combining the two strategies, DAMA enables the model to effectively adapt to data with varying levels of hardness.
• Score: 31.116618294885065
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Direct Preference Optimization (DPO) has shown effectiveness in aligning multi-modal large language models (MLLM) with human preferences. However, existing methods exhibit an imbalanced responsiveness to the data of varying hardness, tending to overfit on the easy-to-distinguish data while underfitting on the hard-to-distinguish data. In this paper, we propose Data- and Model-aware DPO (DAMA) to dynamically adjust the optimization process from two key aspects: (1) a data-aware strategy that incorporates data hardness, and (2) a model-aware strategy that integrates real-time model responses. By combining the two strategies, DAMA enables the model to effectively adapt to data with varying levels of hardness. Extensive experiments on five benchmarks demonstrate that DAMA not only significantly enhances the trustworthiness, but also improves the effectiveness over general tasks. For instance, on the Object-HalBench, our DAMA-7B reduces response-level and mentioned-level hallucination by 90.0% and 95.3%, respectively, surpassing the performance of GPT-4V.

Related papers

• DONOD: Robust 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. We propose DONOD, a lightweight model-intrinsic data pruning method. By filtering out 70% of the full 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)
• More is Less: The Pitfalls of Multi-Model Synthetic Preference Data in DPO Safety Alignment [80.04449725137177]
  Direct Preference Optimization (DPO) has emerged as a simple, yet effective alternative to reinforcement learning from human feedback. Our study reveals a striking, safety-specific phenomenon associated with DPO alignment. Using solely self-generated responses for both chosen and rejected pairs significantly outperforms configurations that incorporate responses from stronger models.
  arXiv  Detail & Related papers  (2025-04-03T00:36:40Z)
• Towards Robust Universal Information Extraction: Benchmark, Evaluation, and Solution [66.11004226578771]
  Existing robust benchmark datasets have two key limitations. They generate only a limited range of perturbations for a single Information Extraction (IE) task. Considering the powerful generation capabilities of Large Language Models (LLMs), we introduce a new benchmark dataset for Robust UIE, called RUIE-Bench. We show that training with only textbf15% of the data leads to an average textbf7.5% relative performance improvement across three IE tasks.
  arXiv  Detail & Related papers  (2025-03-05T05:39:29Z)
• Dynamic Noise Preference Optimization for LLM Self-Improvement via Synthetic Data [51.62162460809116]
  We introduce Dynamic Noise Preference Optimization (DNPO) to ensure consistent improvements across iterations. In experiments with Zephyr-7B, DNPO consistently outperforms existing methods, showing an average performance boost of 2.6%. DNPO shows a significant improvement in model-generated data quality, with a 29.4% win-loss rate gap compared to the baseline in GPT-4 evaluations.
  arXiv  Detail & Related papers  (2025-02-08T01:20:09Z)
• Multimodal Preference Data Synthetic Alignment with Reward Model [23.978820500281213]
  We propose a new framework in generating synthetic data using a reward model as a proxy of human preference for effective multimodal alignment with DPO training. Experiment results indicate that integrating selected synthetic data, such as from generative and rewards models can effectively reduce reliance on human-annotated data.
  arXiv  Detail & Related papers  (2024-12-23T09:29:40Z)
• Star-Agents: Automatic Data Optimization with LLM Agents for Instruction Tuning [71.2981957820888]
  We propose a novel Star-Agents framework, which automates the enhancement of data quality across datasets. The framework initially generates diverse instruction data with multiple LLM agents through a bespoke sampling method. The generated data undergo a rigorous evaluation using a dual-model method that assesses both difficulty and quality.
  arXiv  Detail & Related papers  (2024-11-21T02:30:53Z)
• Enhancing the Reasoning Ability of Multimodal Large Language Models via Mixed Preference Optimization [65.64108848398696]
  We introduce a preference optimization process to enhance the multimodal reasoning capabilities of MLLMs. We develop a simple yet effective method, termed Mixed Preference Optimization (MPO), which boosts multimodal CoT performance. Our model, InternVL2-8B-MPO, achieves an accuracy of 67.0 on MathVista, outperforming InternVL2-8B by 8.7 points and achieving performance comparable to the 10x larger InternVL2-76B.
  arXiv  Detail & Related papers  (2024-11-15T18:59:27Z)
• 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)
• On-the-fly Modulation for Balanced Multimodal Learning [53.616094855778954]
  Multimodal learning is expected to boost model performance by integrating information from different modalities. The widely-used joint training strategy leads to imbalanced and under-optimized uni-modal representations. We propose On-the-fly Prediction Modulation (OPM) and On-the-fly Gradient Modulation (OGM) strategies to modulate the optimization of each modality.
  arXiv  Detail & Related papers  (2024-10-15T13:15:50Z)
• MITA: Bridging the Gap between Model and Data for Test-time Adaptation [68.62509948690698]
  Test-Time Adaptation (TTA) has emerged as a promising paradigm for enhancing the generalizability of models. We propose Meet-In-The-Middle based MITA, which introduces energy-based optimization to encourage mutual adaptation of the model and data from opposing directions.
  arXiv  Detail & Related papers  (2024-10-12T07:02:33Z)
• Bridging and Modeling Correlations in Pairwise Data for Direct Preference Optimization [75.1240295759264]
  We propose an effective framework for Bridging and Modeling Correlations in pairwise data, named BMC. We increase the consistency and informativeness of the pairwise preference signals through targeted modifications. We identify that DPO alone is insufficient to model these correlations and capture nuanced variations.
  arXiv  Detail & Related papers  (2024-08-14T11:29:47Z)
• A Self-Supervised Paradigm for Data-Efficient Medical Foundation Model Pre-training: V-information Optimization Framework [15.413974936297082]
  Self-supervised pre-training medical foundation models on large-scale datasets demonstrate exceptional performance. Recent research challenges this common paradigm by introducing data-effective learning approaches. We introduce V-information into self-supervised pre-training of foundation models to provide a theoretical foundation for sample selection.
  arXiv  Detail & Related papers  (2024-08-13T10:28:54Z)
• Self-Augmented Preference Optimization: Off-Policy Paradigms for Language Model Alignment [104.18002641195442]
  We introduce Self-Augmented Preference Optimization (SAPO), an effective and scalable training paradigm that does not require existing paired data. Building on the self-play concept, which autonomously generates negative responses, we further incorporate an off-policy learning pipeline to enhance data exploration and exploitation.
  arXiv  Detail & Related papers  (2024-05-31T14:21:04Z)
• BiMix: A Bivariate Data Mixing Law for Language Model Pretraining [47.77701041534746]
  The impact of pretraining data composition on model performance remains poorly understood.<n>$textbfBiMix$ provides a systematic framework for understanding and optimizing data mixtures.<n>Our work contributes both theoretical insights into data mixing dynamics and practical tools for enhancing LLM training efficiency.
  arXiv  Detail & Related papers  (2024-05-23T09:44:02Z)
• APrompt4EM: Augmented Prompt Tuning for Generalized Entity Matching [5.92432068962337]
  Generalized Entity Matching (GEM) aims at judging whether two records represented in different formats refer to the same real-world entity. This paper introduces an augmented prompt tuning framework for the challenges, which consists of two main improvements.
  arXiv  Detail & Related papers  (2024-05-08T05:38:56Z)
• When Parameter-efficient Tuning Meets General-purpose Vision-language Models [65.19127815275307]
  PETAL revolutionizes the training process by requiring only 0.5% of the total parameters, achieved through a unique mode approximation technique. Our experiments reveal that PETAL not only outperforms current state-of-the-art methods in most scenarios but also surpasses full fine-tuning models in effectiveness.
  arXiv  Detail & Related papers  (2023-12-16T17:13:08Z)

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.