Debiasing Multimodal Large Language Models via Noise-Aware Preference Optimization

• URL: http://arxiv.org/abs/2503.17928v1
• Date: Sun, 23 Mar 2025 04:00:11 GMT
• Title: Debiasing Multimodal Large Language Models via Noise-Aware Preference Optimization
• Authors: Zefeng Zhang, Hengzhu Tang, Jiawei Sheng, Zhenyu Zhang, Yiming Ren, Zhenyang Li, Dawei Yin, Duohe Ma, Tingwen Liu,
• Abstract summary: We propose using the paradigm of preference optimization to solve the modality bias problem.<n>Specifically, we first construct the dataset by introducing perturbations to reduce the informational content of certain modalities.<n>To address the inevitable noise in automatically constructed data, we combine the noise robust Mean Absolute Error with the Binary Cross Entropy in Direct Preference Optimization.
• Score: 31.741110625305186
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multimodal Large Language Models excel in various tasks, yet often struggle with modality bias, where the model tends to rely heavily on a single modality and overlook critical information in other modalities, which leads to incorrect focus and generating irrelevant responses. In this paper, we propose using the paradigm of preference optimization to solve the modality bias problem, including RLAIFVBias, a debiased preference optimization dataset, and a Noise Aware Preference Optimization algorithm. Specifically, we first construct the dataset by introducing perturbations to reduce the informational content of certain modalities, compelling the model to rely on a specific modality when generating negative responses. To address the inevitable noise in automatically constructed data, we combine the noise robust Mean Absolute Error with the Binary Cross Entropy in Direct Preference Optimization by a negative Box Cox transformation, and dynamically adjust the algorithm noise robustness based on the evaluated noise levels in the data. Extensive experiments validate our approach, demonstrating not only its effectiveness in mitigating modality bias but also its significant role in minimizing hallucinations.

Related papers

• One Goal, Many Challenges: Robust Preference Optimization Amid Content-Aware and Multi-Source Noise [0.0]
  This paper introduces Content-Aware Noise-Resilient Preference Optimization (CNRPO), a novel framework that addresses multiple sources of content-dependent noise in preference learning.<n>We leverage backdoor attack mechanisms to efficiently learn and control various noise sources within a single model.
  arXiv  Detail & Related papers  (2025-03-16T00:22:00Z)
• Pareto Optimization with Robust Evaluation for Noisy Subset Selection [34.83487850400559]
  Subset selection is a fundamental problem in optimization, which has a wide range of applications such as influence and sparse regression. Previous algorithms, including the greedy algorithm and evolutionary evolutionary POSS, either struggle in noisy environments or consume excessive computational resources. We propose a novel approach based on Pareto Optimization with Robust Evaluation for noisy subset selection (PORE), which maximizes a robust evaluation function and minimizes the subset size simultaneously.
  arXiv  Detail & Related papers  (2025-01-12T14:04:20Z)
• Accelerated zero-order SGD under high-order smoothness and overparameterized regime [79.85163929026146]
  We present a novel gradient-free algorithm to solve convex optimization problems. Such problems are encountered in medicine, physics, and machine learning. We provide convergence guarantees for the proposed algorithm under both types of noise.
  arXiv  Detail & Related papers  (2024-11-21T10:26:17Z)
• Self-Evolutionary Large Language Models through Uncertainty-Enhanced Preference Optimization [9.618391485742968]
  Iterative preference optimization has recently become one of the de-facto training paradigms for large language models (LLMs) We present an uncertainty-enhanced textbfPreference textbfOptimization framework to make the LLM self-evolve with reliable feedback. Our framework substantially alleviates the noisy problem and improves the performance of iterative preference optimization.
  arXiv  Detail & Related papers  (2024-09-17T14:05:58Z)
• ROPO: Robust Preference Optimization for Large Language Models [59.10763211091664]
  We propose an iterative alignment approach that integrates noise-tolerance and filtering of noisy samples without the aid of external models. Experiments on three widely-used datasets with Mistral-7B and Llama-2-7B demonstrate that ROPO significantly outperforms existing preference alignment methods.
  arXiv  Detail & Related papers  (2024-04-05T13:58:51Z)
• An Adaptive Cost-Sensitive Learning and Recursive Denoising Framework for Imbalanced SVM Classification [12.986535715303331]
  Category imbalance is one of the most popular and important issues in the domain of classification.<n>We propose a robust learning algorithm based on adaptive cost-sensitivity and recursion.<n> Experimental results show that the proposed general framework is superior to traditional methods in Accuracy, G-mean, Recall and F1-score.
  arXiv  Detail & Related papers  (2024-03-13T09:43:14Z)
• Realistic Noise Synthesis with Diffusion Models [44.404059914652194]
  Deep denoising models require extensive real-world training data, which is challenging to acquire.<n>We propose a novel Realistic Noise Synthesis Diffusor (RNSD) method using diffusion models to address these challenges.
  arXiv  Detail & Related papers  (2023-05-23T12:56:01Z)
• Conditional Denoising Diffusion for Sequential Recommendation [62.127862728308045]
  Two prominent generative models, Generative Adversarial Networks (GANs) and Variational AutoEncoders (VAEs) GANs suffer from unstable optimization, while VAEs are prone to posterior collapse and over-smoothed generations. We present a conditional denoising diffusion model, which includes a sequence encoder, a cross-attentive denoising decoder, and a step-wise diffuser.
  arXiv  Detail & Related papers  (2023-04-22T15:32:59Z)
• The Optimal Noise in Noise-Contrastive Learning Is Not What You Think [80.07065346699005]
  We show that deviating from this assumption can actually lead to better statistical estimators. In particular, the optimal noise distribution is different from the data's and even from a different family.
  arXiv  Detail & Related papers  (2022-03-02T13:59:20Z)
• Adaptive Multi-View ICA: Estimation of noise levels for optimal inference [65.94843987207445]
  Adaptive multiView ICA (AVICA) is a noisy ICA model where each view is a linear mixture of shared independent sources with additive noise on the sources. On synthetic data, AVICA yields better sources estimates than other group ICA methods thanks to its explicit MMSE estimator. On real magnetoencephalograpy (MEG) data, we provide evidence that the decomposition is less sensitive to sampling noise and that the noise variance estimates are biologically plausible.
  arXiv  Detail & Related papers  (2021-02-22T13:10:12Z)
• Bilevel Optimization for Differentially Private Optimization in Energy Systems [53.806512366696275]
  This paper studies how to apply differential privacy to constrained optimization problems whose inputs are sensitive. The paper shows that, under a natural assumption, a bilevel model can be solved efficiently for large-scale nonlinear optimization problems.
  arXiv  Detail & Related papers  (2020-01-26T20:15:28Z)

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.