An Empirical Study on Configuring In-Context Learning Demonstrations for Unleashing MLLMs' Sentimental Perception Capability

2025-05-22 · Daiqing Wu, Dongbao Yang, Sicheng Zhao, Can Ma, Yu Zhou

The advancements in Multimodal Large Language Models (MLLMs) have enabled various multimodal tasks to be addressed under a zero-shot paradigm. This paradigm sidesteps the cost of model fine-tuning, emerging as a dominant trend in practical application. Nevertheless, Multimodal Sentiment Analysis (MSA), a pivotal challenge in the quest for general artificial intelligence, fails to accommodate this convenience. The zero-shot paradigm exhibits undesirable performance on MSA, casting doubt on whether MLLMs can perceive sentiments as competent as supervised models. By extending the zero-shot paradigm to In-Context Learning (ICL) and conducting an in-depth study on configuring demonstrations, we validate that MLLMs indeed possess such capability. Specifically, three key factors that cover demonstrations' retrieval, presentation, and distribution are comprehensively investigated and optimized. A sentimental predictive bias inherent in MLLMs is also discovered and later effectively counteracted. By complementing each other, the devised strategies for three factors result in average accuracy improvements of 15.9% on six MSA datasets against the zero-shot paradigm and 11.2% against the random ICL baseline.

📄 PDF Abstract BibTeX arXiv:2505.16193

Code (0)

등록된 구현이 없습니다.

Tasks

In-Context LearningMultimodal Sentiment Analysis Sentiment Analysis

Lever LM: Configuring In-Context Sequence to Lever Large Vision Language Models

2023-12-15 · Xu Yang, Yingzhe Peng, Haoxuan Ma, Shuo Xu 외

As Archimedes famously said, ``Give me a lever long enough and a fulcrum on which to place it, and I shall move the world'', in this study, we propose to use a tiny Language Model (LM), \eg, a Transformer with 67M parame…

Image Captioning In-Context Learning Language Modelling Question Answering+2

Policy Space Identification in Configurable Environments

2019-09-09 · Alberto Maria Metelli, Guglielmo Manneschi, Marcello Restelli

We study the problem of identifying the policy space of a learning agent, having access to a set of demonstrations generated by its optimal policy. We introduce an approach based on statistical testing to identify the se…

Reason Analogically via Cross-domain Prior Knowledge: An Empirical Study of Cross-domain Knowledge Transfer for In-Context Learning

2026-04-07 · Le Liu, Zhiming Li, Jianzhi Yan, Zike Yuan 외 arxiv

Despite its success, existing in-context learning (ICL) relies on in-domain expert demonstrations, limiting its applicability when expert annotations are scarce. We posit that different domains may share underlying reaso…

Large Language Models Are Latent Variable Models: Explaining and Finding Good Demonstrations for In-Context Learning

2023-01-27 · NeurIPS 2023 11 · Xinyi Wang, Wanrong Zhu, Michael Saxon, Mark Steyvers 외

In recent years, pre-trained large language models (LLMs) have demonstrated remarkable efficiency in achieving an inference-time few-shot learning capability known as in-context learning. However, existing literature has…

Few-Shot Learning GSM8K In-Context Learning Language Modeling+4

Diverse Demonstrations Improve In-context Compositional Generalization

2022-12-13 · Itay Levy, Ben Bogin, Jonathan Berant

In-context learning has shown great success in i.i.d semantic parsing splits, where the training and test sets are drawn from the same distribution. In this setup, models are typically prompted with demonstrations that a…

In-Context Learning Semantic Parsing