StanceFlip: A Comprehensive Multi-Dimensional Benchmark for Multimodal Conversational Stance Flipping Forecasting
作者: Heyan Chai, Xin Li, Wenjie Wang, Jianyang Qin, Chaoyang Li, Lu Wang, Hao Chen, Qing Liao
分类: cs.CL, cs.AI
发布日期: 2026-07-27
备注: 17pages, 8 figures
💡 一句话要点
提出StanceFlip基准以解决多模态对话立场翻转预测问题
🎯 匹配领域: 支柱九:具身大模型 (Embodied Foundation Models)
关键词: 多模态对话 立场检测 情感分析 动态建模 大型语言模型 对话系统 推理机制
📋 核心要点
- 现有对话立场检测方法未能有效捕捉信念的动态演变,尤其在立场反转时表现不足。
- 论文提出StanceFlip基准,设计了多模态立场六元组提取和动态立场翻转归因两个新子任务。
- 实验结果表明,所提方法在六元组提取和翻转触发归因上均超越了强大的多模态大型语言模型基线,取得了最先进的性能。
📝 摘要(中文)
对话立场检测已从静态文本分析转向动态多模态建模。然而,现有基准存在三大关键限制:未能捕捉信念的动态演变,尤其是在立场反转时;难以将情感状态与逻辑推理分离;忽视多模态线索在解决讽刺等语用模糊性中的重要作用。为了解决这些问题,我们提出了StanceFlip基准,旨在对多轮对话中的多模态立场翻转进行预测,涵盖五种模态和多种场景,并包括两个新子任务:1)多模态立场六元组提取,捕捉对话的静态状态快照;2)动态立场翻转归因,跟踪对话中的立场反转及其触发因素。我们还提出了名为ConStaFF的专用框架,基于大型语言模型进行端到端的立场推理,结合了思维立场推理框架和自反验证机制。
🔬 方法详解
问题定义:本论文旨在解决多模态对话中的立场翻转预测问题,现有方法在捕捉信念动态演变和多模态线索的利用上存在不足。
核心思路:提出StanceFlip基准,通过多模态数据和新子任务设计,增强对话立场的动态建模能力,特别是在立场反转时的推理能力。
技术框架:整体框架名为ConStaFF,包含思维立场推理(ToS)模块和自反验证机制,支持多模态信息的融合与立场推理的结构化建模。
关键创新:最重要的创新在于引入了多模态立场六元组提取和动态立场翻转归因两个新子任务,显著提升了对话立场的理解与预测能力。
关键设计:在模型设计中,ToS模块将推理过程分解为多个认知角色,处理跨模态冲突,并推断历史立场轨迹,确保立场推理的准确性和可靠性。实验中采用了特定的损失函数和网络结构,以优化模型性能。
🖼️ 关键图片
📊 实验亮点
实验结果显示,所提出的ConStaFF框架在多模态立场六元组提取和翻转触发归因任务上均达到了最先进的性能,相较于强大的多模态大型语言模型基线,性能提升幅度显著,具体数据未在摘要中提供。
🎯 应用场景
该研究的潜在应用领域包括社交媒体分析、在线客服系统和情感计算等。通过准确预测对话中的立场变化,能够提升人机交互的自然性和有效性,未来可能对情感分析和舆情监测产生深远影响。
📄 摘要(原文)
Conversational stance detection has shifted from static text analysis to dynamic multimodal modeling. However, existing benchmarks exhibit three key limitations: failure to capture the dynamic evolution of beliefs, particularly during stance reversals; difficulty in disentangling affective states from logical reasoning; and neglect of the critical role of multimodal cues in resolving pragmatic ambiguities such as sarcasm. To address these limitations, we propose StanceFlip, a benchmark designed for multimodal conversational stance flipping forecasting over multi-turn dialogues across five modalities and multi-scenarios, which includes two novel subtasks: 1) Multimodal Stance Sextuple Extraction, extracting holder, target, emotion, sentiment, stance, and rationale as static state snapshots of dialogue to capture fine-grained cognitive structures. 2) Dynamic Stance Flip Attribution, tracking stance reversals across the conversation and identifying their underlying triggers. Alongside the dataset, we propose a dedicated framework, named ConStaFF, for Multimodal Conversational Stance Flipping Forecasting (MCSFF). Built upon a large language model, ConStaFF performs end-to-end stance reasoning, with a Thought-of-Stance (ToS) reasoning framework and a self-reflective verification mechanism integrated for structured stance modeling and faithful flip attribution. Specifically, ToS decomposes the reasoning process into specialized cognitive personas to formulate target propositions, resolve cross-modal conflicts, and infer historical stance trajectories. Extensive experiments show that our approach achieves state-of-the-art performance on both sextuple extraction and flip-trigger attribution, outperforming strong multimodal large language model baselines by substantial margins.