Saved in:
Bibliographic Details
Main Authors: Gao, Zhiqiang, Gao, Shihao, Zhang, Zixing, Guo, Yihao, Chen, Hongyu, Han, Jing
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.22603
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912791301980160
author Gao, Zhiqiang
Gao, Shihao
Zhang, Zixing
Guo, Yihao
Chen, Hongyu
Han, Jing
author_facet Gao, Zhiqiang
Gao, Shihao
Zhang, Zixing
Guo, Yihao
Chen, Hongyu
Han, Jing
contents Understanding sentiment in multimodal conversations is a complex yet crucial challenge toward building emotionally intelligent AI systems. The Multimodal Conversational Aspect-based Sentiment Analysis (MCABSA) Challenge invited participants to tackle two demanding subtasks: (1) extracting a comprehensive sentiment sextuple, including holder, target, aspect, opinion, sentiment, and rationale from multi-speaker dialogues, and (2) detecting sentiment flipping, which detects dynamic sentiment shifts and their underlying triggers. For Subtask-I, in the present paper, we designed a structured prompting pipeline that guided large language models (LLMs) to sequentially extract sentiment components with refined contextual understanding. For Subtask-II, we further leveraged the complementary strengths of three LLMs through ensembling to robustly identify sentiment transitions and their triggers. Our system achieved a 47.38% average score on Subtask-I and a 74.12% exact match F1 on Subtask-II, showing the effectiveness of step-wise refinement and ensemble strategies in rich, multimodal sentiment analysis tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2512_22603
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Structured Prompting and LLM Ensembling for Multimodal Conversational Aspect-based Sentiment Analysis
Gao, Zhiqiang
Gao, Shihao
Zhang, Zixing
Guo, Yihao
Chen, Hongyu
Han, Jing
Computation and Language
Understanding sentiment in multimodal conversations is a complex yet crucial challenge toward building emotionally intelligent AI systems. The Multimodal Conversational Aspect-based Sentiment Analysis (MCABSA) Challenge invited participants to tackle two demanding subtasks: (1) extracting a comprehensive sentiment sextuple, including holder, target, aspect, opinion, sentiment, and rationale from multi-speaker dialogues, and (2) detecting sentiment flipping, which detects dynamic sentiment shifts and their underlying triggers. For Subtask-I, in the present paper, we designed a structured prompting pipeline that guided large language models (LLMs) to sequentially extract sentiment components with refined contextual understanding. For Subtask-II, we further leveraged the complementary strengths of three LLMs through ensembling to robustly identify sentiment transitions and their triggers. Our system achieved a 47.38% average score on Subtask-I and a 74.12% exact match F1 on Subtask-II, showing the effectiveness of step-wise refinement and ensemble strategies in rich, multimodal sentiment analysis tasks.
title Structured Prompting and LLM Ensembling for Multimodal Conversational Aspect-based Sentiment Analysis
topic Computation and Language
url https://arxiv.org/abs/2512.22603