# Structured Prompting and LLM Ensembling for Multimodal Conversational Aspect-based Sentiment Analysis

arXiv: https://arxiv.org/abs/2512.22603 · HTML: https://mlsanity.com/paper/2512.22603/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 39 references that are in the map.
- First posted on arXiv 27 Dec 2025.

## Builds on (most cited first, 13 of 13)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [NExT-GPT: Any-to-Any Multimodal LLM](https://mlsanity.com/paper/2309.05519/) (2023)
- [SWIFT:A Scalable lightWeight Infrastructure for Fine-Tuning](https://mlsanity.com/paper/2408.05517/) (2024)
- [On LLMs-Driven Synthetic Data Generation, Curation, and Evaluation: A Survey](https://mlsanity.com/paper/2406.15126/) (2024)
- [Dawn of the transformer era in speech emotion recognition: closing the valence gap](https://mlsanity.com/paper/2203.07378/) (2022)
- [Video-of-Thought: Step-by-Step Video Reasoning from Perception to Cognition](https://mlsanity.com/paper/2501.03230/) (2024)
- [Emotion-Cause Pair Extraction: A New Task to Emotion Analysis in Texts](https://mlsanity.com/paper/1906.01267/) (2019)
- [Video-based Facial Micro-Expression Analysis: A Survey of Datasets, Features and Algorithms](https://mlsanity.com/paper/2201.12728/) (2022)
- [DataDreamer: A Tool for Synthetic Data Generation and Reproducible LLM Workflows](https://mlsanity.com/paper/2402.10379/) (2024)
- [Multi-Granular Multimodal Clue Fusion for Meme Understanding](https://mlsanity.com/paper/2503.12560/) (2025)
- [PanoSent: A Panoptic Sextuple Extraction Benchmark for Multimodal Conversational Aspect-based Sentiment Analysis](https://mlsanity.com/paper/2408.09481/) (2024)
- [Combating Multimodal LLM Hallucination via Bottom-Up Holistic Reasoning](https://mlsanity.com/paper/2412.11124/) (2024)
- [Targeted aspect based multimodal sentiment analysis:an attention capsule extraction and multi-head fusion network](https://mlsanity.com/paper/2103.07659/) (2021)

## Built on by (most cited first, 1 of 1)

- [MAF: Multimodal Adaptive Few-shot Prompting for Sentiment Analysis with MLLMs](https://mlsanity.com/paper/2606.15694/) (2026)

## Abstract (arXiv)

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.