# Enhanced Multimodal Aspect-Based Sentiment Analysis by LLM-Generated Rationales

arXiv: https://arxiv.org/abs/2505.14499 · HTML: https://mlsanity.com/paper/2505.14499/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 33 references that are in the map.
- First posted on arXiv 20 May 2025.

## Builds on (most cited first, 18 of 18)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [Emergent Abilities of Large Language Models](https://mlsanity.com/paper/2206.07682/) (2022)
- [ClipCap: CLIP Prefix for Image Captioning](https://mlsanity.com/paper/2111.09734/) (2021)
- [Knowing What, How and Why: A Near Complete Solution for Aspect-based Sentiment Analysis](https://mlsanity.com/paper/1911.01616/) (2019)
- [Large Language Model Is Not a Good Few-shot Information Extractor, but a Good Reranker for Hard Samples!](https://mlsanity.com/paper/2303.08559/) (2023)
- [Relational Graph Attention Network for Aspect-based Sentiment Analysis](https://mlsanity.com/paper/2004.12362/) (2020)
- [A Unified Generative Framework for Aspect-Based Sentiment Analysis](https://mlsanity.com/paper/2106.04300/) (2021)
- [Adapt or Get Left Behind: Domain Adaptation through BERT Language Model Finetuning for Aspect-Target Sentiment Classification](https://mlsanity.com/paper/1908.11860/) (2019)
- [Open-Domain Targeted Sentiment Analysis via Span-Based Extraction and Classification](https://mlsanity.com/paper/1906.03820/) (2019)
- [Exploiting BERT For Multimodal Target Sentiment Classification Through Input Space Translation](https://mlsanity.com/paper/2108.01682/) (2021)
- [RpBERT: A Text-image Relation Propagation-based BERT Model for Multimodal NER](https://mlsanity.com/paper/2102.02967/) (2021)
- [DeepSentiBank: Visual Sentiment Concept Classification with Deep Convolutional Neural Networks](https://mlsanity.com/paper/1410.8586/) (2014)
- [Vision-Language Pre-Training for Multimodal Aspect-Based Sentiment Analysis](https://mlsanity.com/paper/2204.07955/) (2022)
- [Few-shot Joint Multimodal Aspect-Sentiment Analysis Based on Generative Multimodal Prompt](https://mlsanity.com/paper/2305.10169/) (2023)
- [AoM: Detecting Aspect-oriented Information for Multimodal Aspect-Based Sentiment Analysis](https://mlsanity.com/paper/2306.01004/) (2023)

## Built on by (most cited first, 2 of 2)

- [TimeMosaic: Temporal Heterogeneity Guided Time Series Forecasting via Adaptive Granularity Patch and Segment-wise Decoding](https://mlsanity.com/paper/2509.19406/) (2025)
- [Explainable Multimodal Aspect-Based Sentiment Analysis with Dependency-guided Large Language Model](https://mlsanity.com/paper/2601.06848/) (2026)

## Abstract (arXiv)

There has been growing interest in Multimodal Aspect-Based Sentiment Analysis (MABSA) in recent years. Existing methods predominantly rely on pre-trained small language models (SLMs) to collect information related to aspects and sentiments from both image and text, with an aim to align these two modalities. However, small SLMs possess limited capacity and knowledge, often resulting in inaccurate identification of meaning, aspects, sentiments, and their interconnections in textual and visual data. On the other hand, Large language models (LLMs) have shown exceptional capabilities in various tasks by effectively exploring fine-grained information in multimodal data. However, some studies indicate that LLMs still fall short compared to fine-tuned small models in the field of ABSA. Based on these findings, we propose a novel framework, termed LRSA, which combines the decision-making capabilities of SLMs with additional information provided by LLMs for MABSA. Specifically, we inject explanations generated by LLMs as rationales into SLMs and employ a dual cross-attention mechanism for enhancing feature interaction and fusion, thereby augmenting the SLMs' ability to identify aspects and sentiments. We evaluated our method using two baseline models, numerous experiments highlight the superiority of our approach on three widely-used benchmarks, indicating its generalizability and applicability to most pre-trained models for MABSA.