Curiouser and Curiouser: LLMs' Hallucination Wonderland

Title: Curiouser and Curiouser: LLMs' Hallucination Wonderland

Abstract: Large Language Models (LLMs) are increasingly being integrated into various applications. However, these models are not perfect and can generate false, inaccurate, or even harmful
output, which we refer to as hallucination. To ensure the safe and effective deployment of LLMs in real-life scenarios, it is essential to understand the causes of hallucination and develop strategies to mitigate them.
I believe many enthusiasts from our community are familiar with models like ChatGPT, LLaMa2, and others. Let's go beyond the format of a classical presentation to more live session, like stand-up. Bring your own story and share your experience of LLM’s hallucinations. Also, we will explore ways to address these issues without expensive fine-tuning, such as prompt engineering, one- and few-shot learning, reasoning chains, and agents as possible solutions to overcome LLM hallucination. By working together, we can enhance the reliability and accuracy of models and unlock their full potential in various applications.

Program:
17:30 Welcome chat
18:00 Talk
18:50 Discussion
19:10 Networking (Impact Hub)

About MLMUs:
Machine Learning Meetups (MLMU) is an independent platform for people interested in Machine Learning, Information Retrieval, Natural Language Processing, Computer Vision, Pattern Recognition, Data Journalism, Artificial Intelligence, Agent Systems and all the related topics. MLMU is a regular community meeting usually consisting of a talk, a discussion and subsequent networking. Except of Prague, MLMU also spread to Brno, Bratislava and Košice.