A Comparative Study of Task Adaptation Techniques of Large Language Models for Identifying Sustainable Development Goals

2025/06/18 by Andrea Cadeddu, Cadeddu, Andrea, Alessandro Chessa +15
Computer Science · Engineering · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Online Learning and Analytics #Smart Cities and Technologies

paper · pdf · doi:10.48550/arxiv.2506.15208

openalex publication_date 2025/06/18 · openalex created_date 2025/10/19 · openalex updated_date 2026/07/28

Abstract

In 2012, the United Nations introduced 17 Sustainable Development Goals (SDGs) aimed at creating a more sustainable and improved future by 2030. However, tracking progress toward these goals is difficult because of the extensive scale and complexity of the data involved. Text classification models have become vital tools in this area, automating the analysis of vast amounts of text from a variety of sources. Additionally, large language models (LLMs) have recently proven indispensable for many natural language processing tasks, including text classification, thanks to their ability to recognize complex linguistic patterns and semantics. This study analyzes various proprietary and open-source LLMs for a single-label, multi-class text classification task focused on the SDGs. Then, it also evaluates the effectiveness of task adaptation techniques (i.e., in-context learning approaches), namely Zero-Shot and Few-Shot Learning, as well as Fine-Tuning within this domain. The results reveal that smaller models, when optimized through prompt engineering, can perform on par with larger models like OpenAI's GPT (Generative Pre-trained Transformer).

Citations

• Knowledge graph validation by integrating LLMs and human-in-the-loop
• CS-KG 2.0: A Large-scale Knowledge Graph of Computer Science
• Optimizing Large Language Models for ESG Activity Detection in Financial Texts
• Large language models for scholarly ontology generation: An extensive analysis in the engineering field
• A Survey on Knowledge Organization Systems of Research Fields: Resources and Challenges
• Stay Tuned: An Empirical Study of the Impact of Hyperparameters on LLM Tuning in Real-World Applications
• Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone
• MiniCheck: Efficient Fact-Checking of LLMs on Grounding Documents
• Language Models for Text Classification: Is In-Context Learning Enough?
• Artificial Intelligence for Literature Reviews: Opportunities and Challenges
• Pushing The Limit of LLM Capacity for Text Classification
• Mixtral of Experts
• Zephyr: Direct Distillation of LM Alignment
• Mistral 7B
• Large Language Models in Finance: A Survey
• Mining Patents with Large Language Models Elucidates the Chemical Function Landscape
• Open, Closed, or Small Language Models for Text Classification?
• Llama 2: Open Foundation and Fine-Tuned Chat Models
• GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints
• Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyond
• Knowledge Graphs: Opportunities and Challenges
• GPT-4 Technical Report
• Scaling Instruction-Finetuned Language Models
• Finetuned Language Models Are Zero-Shot Learners
• A Survey on Text Classification: From Shallow to Deep Learning
• OSDG -- Open-Source Approach to Classify Text Data by UN Sustainable Development Goals (SDGs)
• Language Models are Few-Shot Learners
• Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
• Attention Is All You Need
• Long Short-Term Memory
• BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

Related

• A Comparative Study of Task Adaptation Techniques of Large Language Models for Identifying Sustainable Development Goals
• Large Language Models for Text Classification: From Zero-Shot Learning to Instruction-Tuning
• RAFT: A Real-World Few-Shot Text Classification Benchmark
• Data Generation Using Large Language Models for Text Classification: An Empirical Case Study
• A Critical Review of Large Language Models: Sensitivity, Bias, and the Path Toward Specialized AI