A Critical Review of Large Language Models: Sensitivity, Bias, and the Path Toward Specialized AI

TL;DR

This paper critically reviews large language models, highlighting their biases and sensitivities, and emphasizes the importance of specialized models for precise, unbiased SDG detection in text data.

Contribution

It compares general-purpose LLMs with specialized SDG detection models, demonstrating the benefits of specialization for accuracy and relevance.

Findings

Specialized models outperform GPT-3.5 in SDG relevance

GPT-3.5 offers broader coverage but less precision

Model selection should consider task requirements and transparency

Abstract

This paper examines the comparative effectiveness of a specialized compiled language model and a general-purpose model like OpenAI's GPT-3.5 in detecting SDGs within text data. It presents a critical review of Large Language Models (LLMs), addressing challenges related to bias and sensitivity. The necessity of specialized training for precise, unbiased analysis is underlined. A case study using a company descriptions dataset offers insight into the differences between the GPT-3.5 and the specialized SDG detection model. While GPT-3.5 boasts broader coverage, it may identify SDGs with limited relevance to the companies' activities. In contrast, the specialized model zeroes in on highly pertinent SDGs. The importance of thoughtful model selection is emphasized, taking into account task requirements, cost, complexity, and transparency. Despite the versatility of LLMs, the use of specialized models is suggested for tasks demanding precision and accuracy. The study concludes by encouraging further research to find a balance between the capabilities of LLMs and the need for domain-specific expertise and interpretability.