# An overview of model uncertainty and variability in LLM-based sentiment analysis. Challenges, mitigation strategies and the role of explainability

arXiv: https://arxiv.org/abs/2504.04462 · HTML: https://mlsanity.com/paper/2504.04462/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 40 references that are in the map.
- First posted on arXiv 6 Apr 2025.

## Builds on (most cited first, 22 of 22)

- [Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI](https://mlsanity.com/paper/1910.10045/) (2019)
- [Explainability for Large Language Models: A Survey](https://mlsanity.com/paper/2309.01029/) (2023)
- [Sentiment Analysis in the Era of Large Language Models: A Reality Check](https://mlsanity.com/paper/2305.15005/) (2023)
- [Benchmarking LLMs via Uncertainty Quantification](https://mlsanity.com/paper/2401.12794/) (2024)
- [Explainable Artificial Intelligence (XAI) 2.0: A Manifesto of Open Challenges and Interdisciplinary Research Directions](https://mlsanity.com/paper/2310.19775/) (2023)
- [A Survey on Uncertainty Quantification of Large Language Models: Taxonomy, Open Research Challenges, and Future Directions](https://mlsanity.com/paper/2412.05563/) (2024)
- [Predicting trends in the quality of state-of-the-art neural networks without access to training or testing data](https://mlsanity.com/paper/2002.06716/) (2020)
- [From Understanding to Utilization: A Survey on Explainability for Large Language Models](https://mlsanity.com/paper/2401.12874/) (2024)
- [LLM Voting: Human Choices and AI Collective Decision Making](https://mlsanity.com/paper/2402.01766/) (2024)
- [A Taxonomy for Human-LLM Interaction Modes: An Initial Exploration](https://mlsanity.com/paper/2404.00405/) (2024)
- [Exploring the Sensitivity of LLMs' Decision-Making Capabilities: Insights from Prompt Variation and Hyperparameters](https://mlsanity.com/paper/2312.17476/) (2023)
- [CompactifAI: Extreme Compression of Large Language Models using Quantum-Inspired Tensor Networks](https://mlsanity.com/paper/2401.14109/) (2024)
- [Generative AI Text Classification using Ensemble LLM Approaches](https://mlsanity.com/paper/2309.07755/) (2023)
- [MiniPLM: Knowledge Distillation for Pre-Training Language Models](https://mlsanity.com/paper/2410.17215/) (2024)
- [Understanding the Uncertainty of LLM Explanations: A Perspective Based on Reasoning Topology](https://mlsanity.com/paper/2502.17026/) (2025)
- [An Overview of Large Language Models for Statisticians](https://mlsanity.com/paper/2502.17814/) (2025)
- [An Empirical Analysis of Uncertainty in Large Language Model Evaluations](https://mlsanity.com/paper/2502.10709/) (2025)
- [Large Language Models Meet Text-Centric Multimodal Sentiment Analysis: A Survey](https://mlsanity.com/paper/2406.08068/) (2024)
- [Language Agents as Digital Representatives in Collective Decision-Making](https://mlsanity.com/paper/2502.09369/) (2025)
- [Comparative Analysis of Pooling Mechanisms in LLMs: A Sentiment Analysis Perspective](https://mlsanity.com/paper/2411.14654/) (2024)
- [Uncertainty Quantification and Decomposition for LLM-based Recommendation](https://mlsanity.com/paper/2501.17630/) (2025)
- [Rethinking the Uncertainty: A Critical Review and Analysis in the Era of Large Language Models](https://mlsanity.com/paper/2410.20199/) (2024)

## Built on by (most cited first, 15 of 15)

- [AgentNoiseBench: Benchmarking Robustness of Tool-Using LLM Agents Under Noisy Condition](https://mlsanity.com/paper/2602.11348/) (2026)
- [Robustness in Large Language Models: A Survey of Mitigation Strategies and Evaluation Metrics](https://mlsanity.com/paper/2505.18658/) (2025)
- [Failure Modes in LLM Systems: A System-Level Taxonomy for Reliable AI Applications](https://mlsanity.com/paper/2511.19933/) (2025)
- [Learning to Act under Noise: Enhancing Agent Robustness via Noisy Environments](https://mlsanity.com/paper/2605.27209/) (2026)
- [The Narrative Continuity Test: A Conceptual Framework for Evaluating Identity Persistence in AI Systems](https://mlsanity.com/paper/2510.24831/) (2025)
- [Understanding Persuasive Interactions between Generative Social Agents and Humans: The Knowledge-based Persuasion Model (KPM)](https://mlsanity.com/paper/2602.11483/) (2026)
- [Preregistration for Experiments with AI Agents](https://mlsanity.com/paper/2606.11217/) (2026)
- [Triadic Fusion of Cognitive, Functional, and Causal Dimensions for Explainable LLMs: The TAXAL Framework](https://mlsanity.com/paper/2509.05199/) (2025)
- [Uncertainty and Fairness Awareness in LLM-Based Recommendation Systems](https://mlsanity.com/paper/2602.02582/) (2026)
- [Copyright Detective: A Forensic System to Evidence LLMs Flickering Copyright Leakage Risks](https://mlsanity.com/paper/2602.05252/) (2026)
- [Responsible AI for General-Purpose Systems: Overview, Challenges, and A Path Forward](https://mlsanity.com/paper/2601.13122/) (2026)
- [Beyond Confidence: The Rhythms of Reasoning in Generative Models](https://mlsanity.com/paper/2602.10816/) (2026)
- [Comparing Semantic Navigation in Humans and Large Language Models using Natural Language Processing](https://mlsanity.com/paper/2607.12195/) (2026)
- [Measuring and Improving Behavioral Consistency in Large Language Models through Fact-Heuristic-Emotion State Enforcement](https://mlsanity.com/paper/2607.24765/) (2026)
- [SOVER: Formal Certification of Optimization Reformulations via LLM-Assisted SMT Verification](https://mlsanity.com/paper/2609.00728/) (2026)

## Abstract (arXiv)

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.