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

Send download link to:

Read next

Uncover Hidden Threats: The Essential Role of Adverse Media Monitoring in Compliance
09. 04. 2024 - 8 min read

Uncover Hidden Threats: The Essential Role of Adverse Media Monitoring in Compliance

Adverse media screening is a crucial part of customer due diligence (CDD). These checks help companies verify customers' identities and assess their risk profiles. CDD is a regulatory requirement for companies entering into business relationships with a customer and is a big part of AML and KYC directives.

Read more
Unveiling the Power of AI: Semantic Visions’ Strategy for Technological Advancement
03. 04. 2024 - 5 min read

Unveiling the Power of AI: Semantic Visions’ Strategy for Technological Advancement

A team of dedicated experts within Semantic Visions drive AI innovation and introduce applications into its business. All operational branches of SV deliveries are currently exploiting the leading-edge technology that allows for advanced automation, unparalleled data processing and informed decision making.

Read more
The Benefits of Applying Semantic Visions’ Screening and Monitoring Services
27. 03. 2024 - 11 min read

The Benefits of Applying Semantic Visions’ Screening and Monitoring Services

We interviewed Anna Polverari, the Head Ontologist at Semantic Visions. She spoke to us about her team and their role. We were offered an expert insight into how big data is extracted, structured and delivered to the client. Anna further explained their robust approach within the vast semantic computational capacity of their technology. Finally, we learned how SV applications can be deployed to either historically screen data or monitor global business operations in near-real time..

Read more
Exploring the Transformative Power of ESG Indexes
21. 03. 2024 - 6 min read

Exploring the Transformative Power of ESG Indexes

ESG indexes have become critical benchmarks within the investment arena, steering investors towards businesses that are not only financially robust but also adhere to sustainable and ethical practices. However, the benefits of achieving high ESG...

Read more
Leveraging Open Source Intelligence for Improved Supply Chain Risk Management
14. 02. 2024 - 1 min read

Leveraging Open Source Intelligence for Improved Supply Chain Risk Management

Unlock the secrets to fortified supply chain resilience with our latest white paper, "Leveraging Open Source Intelligence for Improved Supply Chain Risk Management." Delve into the dynamic landscape of global supply chains, addressing regulatory compliance, Brexit, COVID-19, and geopolitical conflicts.

Read more
The AI Revolution: The Surge of AI Adoption Across Industries
15. 04. 2024 - 2 min read

The AI Revolution: The Surge of AI Adoption Across Industries

In the span of just five years, artificial intelligence (AI) has shifted from a frontier technology to a fundamental component of industry innovation and efficiency. This article aims to unravel the dynamic journey of AI adoption across various sectors from January 2019 to February 2024.

Read more
The Top 3 S&P 500 Companies with Proactive ESG Initiatives in Q1 2024
11. 04. 2024 - 4 min read

The Top 3 S&P 500 Companies with Proactive ESG Initiatives in Q1 2024

In the first quarter of 2024, the S&P 500 index showcased remarkable ESG progress, with several companies making significant strides in sustainability, social responsibility, and technological innovation. Among these, Amazon, NVIDIA, and Ford stood out...

Read more

Ready to see it in action?

Request a demo