Share this article
09. 10. 2023

2 min read

Unlocking AI Insights: Key Takeaways from Working with Large Language Models

Author

Robert Eckstein, Machine Learning Engineer, and Martin Ludvík, Head of AI

The advancements in artificial intelligence, particularly with large language models (LLMs), have had a significant impact on various sectors. As Semantic Visions is in the process of exploring LLMs capabilities and integrating these models into our workflows, we have encountered challenges, surprises, and many learning opportunities. In this article, we will share key takeaways from our experiences, offering insights for both technical enthusiasts and businesses looking to leverage these AI tools. In our exploration, Semantic Vision’s machine learning team focused on five core areas using LLMs’ capabilities: Topic Classification, Named Entity Recognition (NER), Text Paraphrasing, Knowledge Graph Population, and Victim/Aggressor Role Labeling.

Key Takeaways

  • Topic Classification:
    • Large Language Model (LLM) fine-tuning is now an almost trivial task with OpenAI tools.
  • Name Entity Recognition:
    • While Large Language Models excel in many tasks, specialized models designed and optimized for specific applications can outperform them. Named Entity Recognition is one such example, where specialized models are, for the time being, better.
  • Text Paraphrasing Findings:
    • Text paraphrasing and summarization with GPT models is very impressive and already suitable for production. GPT 3.5 Davinci is slightly better than ChatGPT 3.5.
  • Knowledge Graph Population Findings:
    • Using LLMs, transforming unstructured data into knowledge graphs has become more feasible than ever.
  • Victim/Aggressor Role Labeling:
    • Fine-tuned Llama2 model with 13 billion parameters provided on average 10% better accuracy on the Victim/Aggressor task than the much larger ChatGPT 3.5 model, with 175 billion parameters.

——————————————————————————————————————

You can find the full version of the whitepaper here:

Ready to dive deeper into the insights and knowledge offered in our whitepaper? Discover the full version today for a comprehensive look at working with Large Language Models and expert analysis. Click the link below to access the complete whitepaper and stay ahead of the curve.

[download_after_email id=”615″]

Read next

Mastering Supply Chain Complexity Through Advanced Multi-Tier Mapping
24. 01. 2025 - 3 min read

Mastering Supply Chain Complexity Through Advanced Multi-Tier Mapping

Global supply chains are increasingly complex and interconnected, creating challenges for businesses to identify risks and ensure resilience beyond their immediate suppliers. Semantic Visions specialises in addressing these challenges through advanced supply chain mapping and...

Read more
How automation is solving logistics’ biggest problems in 2025
24. 01. 2025 - 9 min read

How automation is solving logistics’ biggest problems in 2025

Article about automation in logistics was originaly published on Freight Waves, link to the original article. As the logistics industry prepares for a more positive 2025, the potential for automation — utilizing machine learning and...

Read more
What Are Market Sentiment Indicators and Why Do They Matter?
21. 01. 2025 - 14 min read

What Are Market Sentiment Indicators and Why Do They Matter?

Market sentiment indicators provide invaluable insights into the collective mood and expectations of investors, businesses, and policymakers. They act as a barometer, reflecting whether markets are optimistic (bullish sentiment) or pessimistic (bearish sentiment) about the...

Read more

Ready to see it in action?

Let's meet