An overview of model uncertainty and variability in LLM-based sentiment analysis. Challenges, mitigation strategies and the role of explainability
Preprint
Abstract
Large Language Models (LLMs) have significantly advanced sentiment analysis, yet their inherent uncertainty and variability pose critical challenges to achieving reliable and consistent outcomes. This paper systematically explores the Model Variability Problem (MVP) in LLM-based sentiment analysis, characterized by inconsistent sentiment classification, polarization, and uncertainty arising from stochastic inference mechanisms, prompt sensitivity, and biases in training data. We analyze the core causes of MVP, presenting illustrative examples and a case study to highlight its impact. In addition, we investigate key challenges and mitigation strategies, paying particular attention to the role of temperature as a driver of output randomness and emphasizing the crucial role of explainability in improving transparency and user trust. By providing a structured perspective on stability, reproducibility, and trustworthiness, this study helps develop more reliable, explainable, and robust sentiment analysis models, facilitating their deployment in high-stakes domains such as finance, healthcare, and policymaking, among others.Keywords
All Related Versions
This publication has 20 references indexed in Scilit:
- Large language models meet text-centric multimodal sentiment analysis: a surveyScience China Information Sciences, 2025
- Reflections and attentiveness on eXplainable Artificial Intelligence (XAI). The journey ahead from criticisms to human–AI collaborationInformation Fusion, 2025
- ChatGPT as a voting application in direct democracySwiss Political Science Review, 2025
- Beyond transparency and explainability: on the need for adequate and contextualized user guidelines for LLM useEthics and Information Technology, 2024
- Sentiment Analysis in the Age of Generative AICustomer Needs and Solutions, 2024
- Explainable Artificial Intelligence (XAI) 2.0: A manifesto of open challenges and interdisciplinary research directionsInformation Fusion, 2024
- Explainable Artificial Intelligence (XAI): What we know and what is left to attain Trustworthy Artificial IntelligenceInformation Fusion, 2023
- A survey on sentiment analysis methods, applications, and challengesArtificial Intelligence Review, 2022
- Sentiment Analysis based Multi-Person Multi-criteria Decision Making methodology using natural language processing and deep learning for smarter decision aid. Case study of restaurant choice using TripAdvisor reviewsInformation Fusion, 2021
- Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AIInformation Fusion, 2020