Multimodal Large Language Models with Adaptive Preference Optimization for Sequential Recommendation

TL;DR

This paper introduces HaNoRec, a multimodal LLM framework that improves sequential recommendation by adaptively optimizing user preferences through hardness-aware and noise-regularized methods, addressing cross-modal bias.

Contribution

It proposes a novel training paradigm that dynamically balances sample difficulty and enhances cross-modal semantic alignment in multimodal recommendation models.

Findings

HaNoRec outperforms existing methods on benchmark datasets.

Dynamic weighting improves training on hard examples.

Gaussian perturbation reduces modality bias.

Abstract

Recent advances in Large Language Models (LLMs) have opened new avenues for sequential recommendation by enabling natural language reasoning over user behavior sequences. A common approach formulates recommendation as a language modeling task, where interaction histories are transformed into prompts and user preferences are learned via supervised fine-tuning. However, these methods operate solely in the textual modality and often miss users' fine-grained interests, especially when shaped by rich visual signals such as product images or movie posters. Multimodal Large Language Models (MLLMs) offer a promising alternative by aligning text and vision in a shared semantic space. A prevalent training paradigm applies Supervised Fine-Tuning (SFT) followed by Direct Preference Optimization (DPO) to model user preferences. Yet, two core challenges remain: 1) Imbalanced sample hardness, where random negative sampling causes overfitting on easy examples and under-training on hard ones; 2) Cross-modal semantic bias, where the fixed reference model in DPO prevents the policy model from correcting modality misalignments--especially over long sequences. To address these issues, we propose a Multimodal LLM framework that integrates Hardness-aware and Noise-regularized preference optimization for Recommendation (HaNoRec). Specifically, HaNoRec dynamically adjusts optimization weights based on both the estimated hardness of each training sample and the policy model's real-time responsiveness, prioritizing harder examples. It further introduces Gaussian-perturbed distribution optimization on output logits to enhance cross-modal semantic consistency and reduce modality bias inherited from the reference model.