MAF: 面向情感分析的多模态自适应少样本提示方法
MAF: Multimodal Adaptive Few-shot Prompting for Sentiment Analysis with MLLMs
AI总结：
提出MAF框架，通过动态检索与查询相关的多模态示例，利用轻量级系数生成网络实时融合多模态相似度，结合多数投票提升MLLM在情感分析中的性能。
摘要：
多模态大语言模型（MLLMs）在理解复杂多模态内容方面展现了卓越的能力。然而，它们在情感分析中的性能对提示设计高度敏感，导致静态、统一应用的提示本质上无法捕捉不同输入中变化的细微多模态线索。为了解决这一局限性，我们提出了一种多模态自适应少样本提示（MAF）框架，该框架动态检索并整合与查询相关的示例，以上下文敏感的方式激发MLLM的情感推理能力。MAF构建了一个示例检索模块，整体编码面部表情、场景上下文和文本语义，并引入唇部运动幅度检测机制以在多人物场景中准确识别说话者。与传统的固定权重融合不同，我们训练了一个轻量级系数生成网络，实时输出查询条件的融合权重，从而实现多模态相似度分数的加权聚合，以检索最具信息量的前K个示例。通过MLLM生成的多个候选输出进行多数投票，进一步增强了预测稳定性。在公开基准数据集上的大量实验表明，MAF相比相应的骨干变体取得了显著且一致的性能提升，并与强大的多模态情感分析基线保持竞争力。
英文摘要：
Multimodal large language models (MLLMs) have demonstrated remarkable capabilities in understanding complex multimodal content. However, their performance in sentiment analysis exhibits acute sensitivity to prompt design, rendering static, uniformly applied prompts inherently suboptimal for capturing the nuanced multimodal cues that vary across inputs. To address this limitation, we propose a Multimodal Adaptive Few-Shot Prompting (MAF) framework, which dynamically retrieves and integrates query-relevant demonstrations to elicit the sentiment reasoning capabilities of MLLMs in a context-sensitive manner. MAF constructs a demonstration retrieval module that holistically encodes facial expressions, scene context, and textual semantics, with a lip movement amplitude detection mechanism introduced for accurate speaker identification in multi-person scenarios. Departing from conventional fixed-weight fusion, a lightweight coefficient generation network is trained to output query-conditioned fusion weights in real time, enabling weighted aggregation of multimodal similarity scores to retrieve the top-K most informative demonstrations. Prediction stability is further enhanced through majority voting over multiple candidate outputs generated by the MLLM. Extensive experiments on public benchmark datasets demonstrate that MAF achieves substantial and consistent performance improvements over the corresponding backbone variants and remains competitive with strong multimodal sentiment-analysis baselines.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
