Exploring LLMs: Building, Fine-Tuning and Detection

Exploring LLMs: Building, Fine-Tuning and Detection
We are excited to invite anyone curious about AI, whether you’re a software engineer, data scientist, or simply interested in understanding how large language models work, to join us for an insightful session at our Tel Aviv office. During this event, you will hear from two expert speakers who will share their experiences in building and fine-tuning LLMs for specific tasks. They will discuss the intricacies of how LLMs work, how to adjust them for specialized applications, and methods for detecting their presence in generated text. Whether you're new to LLMs or have hands-on experience, you’ll leave with practical insights into fine-tuning and detecting LLMs, actionable techniques you can apply, and fresh inspiration for your AI projects.

When: Tuesday, January 28, 2025, from 17:30 to 19:30 IST
Where: Alon Tower #2, 94 Yigal Alon St., Floor 27, Tel Aviv

Agenda:
17:30: Welcome: Networking, Food and Drinks

18:00: Fine-Tuning Large Language Models: Techniques and Approaches for Task-Specific Adaptation
Mike Erlihson, Head of AI, Cyber Stealth
In the talk, Mike will explain why and how fine-tuning is essential for Large Language Models (LLMs). He’ll cover key techniques like Supervised Fine-Tuning (SFT) and Reinforcement Learning with Human Feedback (RLHF), as well as efficient methods and alternatives like in-context learning (ICL) and retrieval-augmented generation (RAG). By the end, you'll understand how to adapt LLMs for specific tasks and improve their performance in specialized applications.

18:45: Detecting AI-Generated Texts
James Eiger, Sr. Data Scientist, DoubleVerify
While LLMs vary in training methods, data, pre-prompts, and limitations, they mostly operate under a similar framework. As such, by leveraging how they operate, we are able to detect texts generated by a wide variety of LLMs with a high degree of accuracy. James will explain how texts are generated and how we can build features around this to detect when a text has been generated by AI.

See you there!