LLaVAC: Fine-tuning LLaVA as a Multimodal Sentiment Classifier

T. Chay-intr, Y. Chen, K. Viriyayudhakorn, T. Theeramunkong
2/5/2025
cs.CL

Official code: tchayintr/LLaVAC (0 stars, last commit 2025-01-02).

Abstract

We present LLaVAC, a method for constructing a classifier for multimodal sentiment analysis. This method leverages fine-tuning of the Large Language and Vision Assistant (LLaVA) to predict sentiment labels across both image and text modalities. Our approach involves designing a structured prompt that incorporates both unimodal and multimodal labels to fine-tune LLaVA, enabling it to perform sentiment classification effectively. Experiments on the MVSA-Single dataset demonstrate that LLaVAC outperforms existing methods in multimodal sentiment analysis across three data processing procedures. The implementation of LLaVAC is publicly available at https://github.com/tchayintr/llavac.

View on arXivView PDF

Code Implementations(1)

tchayintr/LLaVACOfficial100%
00Jan 2, 20251 years ago

Similar Papers

Exploring Large Language Models for Multimodal Sentiment Analysis: Challenges, Benchmarks, and Future Directions

83% match2024

LLaVA-Plus: Learning to Use Tools for Creating Multimodal Agents

82% match1 repo7692023

Multimodal Emotion Recognition and Sentiment Analysis in Multi-Party Conversation Contexts

81% match1 repo142025

Dynamic Multimodal Sentiment Analysis: Leveraging Cross-Modal Attention for Enabled Classification

80% match2025

LLLaVA-Critic: Learning to Evaluate Multimodal Models

80% match2024

Resource-Limited Joint Multimodal Sentiment Reasoning and Classification via Chain-of-Thought Enhancement and Distillation

80% match2025

Cite this paper

@article{chayintr2025llavac,
  title  = {LLaVAC: Fine-tuning LLaVA as a Multimodal Sentiment Classifier},
  author = {T. Chay-intr and Y. Chen and K. Viriyayudhakorn and T. Theeramunkong},
  year   = {2025},
  eprint = {2502.02938},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2502.02938v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2502.02938.svg)](https://codeofpaper.com/paper/2502.02938)

Discussion