Multi-Stage Evolutionary Model Merging with Meta Data Driven Curriculum Learning for Sentiment-Specialized Large Language Modeling

2024-12-13

Decision Support Systems

AI Summary

This work addresses the challenge that existing large language models struggle to balance accuracy and generalization in multi-task sentiment analysis. To this end, the authors propose a novel framework that integrates instruction tuning, an evolutionary algorithm-driven multi-stage model ensemble, and metadata-guided curriculum learning. This approach represents the first effort to combine task metadata–driven curriculum learning with evolutionary model ensembling, enabling efficient customization for sentiment analysis tasks. Experimental results demonstrate that the proposed method significantly outperforms baseline large language models across multiple sentiment analysis subtasks, achieving notable improvements in both prediction accuracy and cross-task generalization performance.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: (Large) Language Models
• Search and Optimization: Metareasoning and Metaheuristics

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Large language models for search
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

The emergence of large language models (LLMs) has significantly transformed natural language processing (NLP), enabling more generalized models to perform various tasks with minimal training. However, traditional sentiment analysis methods, which focus on individual tasks such as sentiment classification or aspect-based analysis, are not practical for real-world applications that usually require handling multiple tasks. While offering flexibility, LLMs in sentiment-specific tasks often fall short of the required accuracy. Techniques like fine-tuning and evolutionary model merging help integrate models into a unified framework, which can improve the learning performance while reducing computational costs. The use of task meta-data and curriculum learning to optimize learning processes remains underexplored, while sentiment analysis is a critical task in NLP that requires high accuracy and scalability across multiple subtasks. In this study, we propose a hybrid learning model called Multi-stage Evolutionary Model Merging with Meta data driven Curriculum Learning (MEM-MCL), to enhance the sentiment analysis in large language modeling. In particular, expert models are created through instruction tuning for specific sentiment tasks and then merged using evolutionary algorithms to form a unified model. The merging process is optimized with weak data to enhance performance across tasks. The curriculum learning is incorporated to provide a learning sequence based on task difficulty, improving knowledge extraction from LLMs. Experiment results demonstrate that the proposed MEM-MCL model outperforms conventional LLMs in a majority of sentiment analysis tasks, achieving superior results across various subtasks.

Problem

• sentiment analysis
• large language models
• multi-task learning
• model accuracy
• scalability

Innovation

• Evolutionary Model Merging
• Curriculum Learning
• Meta-data-driven
• Sentiment-specialized LLM
• Instruction Tuning