Manchester October Meetup

Network, learn, ask a question, meet other folks - these are all things that happen at user group events. These events are a really great opportunity to socialise in an informal learning experience.

Remember to tell your friends and the people you work with; make sure you register as soon as you can.

In-Person only event. Not being recorded.

Please complete the registration form with your full name and organisation you are from - we only collect this information to give to building security to let you into the event.

17:45 – 18:00 Intro and updates
18:00 – 19:00 Juliana Smith - Ethical Storytelling: Keeping Your Visuals on the Right Side of Truth.
Have you ever seen a headline that felt shocking, urgent, or even scary, only to discover that once you dug into the data, the story didn’t quite hold up? That moment of realisation is where ethics in storytelling begin.

This session explores how sampling bias and the framing effect quietly shape data stories, often without malicious intent, yet with very real consequences. You’ll see how technically “correct” data can still distort understanding, steer decisions, and undermine trust through what’s included, what’s excluded, and how the narrative is constructed.

We then turn to responsibility. Using real examples, we’ll look at how to surface data limitations, avoid manipulative framing and headlines, and design visualisations that inform rather than mislead. You’ll leave with practical techniques for keeping your visuals on the right side of truth.

If you care about trust, integrity, and the real‑world impact of your data stories, this session will change how you design them.

19:00 – 19:30 Break & Pizza
19:30 – 20:30 Shubhangi Goyal - Evaluation of LLMs using prompt engineering
In this session, I will discuss how prompt engineering can be leveraged to evaluate the performance, reliability, and limitations of Large Language Models (LLMs). By systematically varying prompts, we uncover model behavior across various tasks, including reasoning, summarization, and code generation. We’ll discuss prompt-based benchmarking methods, prompt sensitivity, and how to design effective evaluation frameworks.
Takeaways:

• Understand the role of prompt design in LLM evaluation.
• Learn techniques to test reasoning, bias, and robustness via prompts.
• Explore limitations of prompt-based metrics and how to mitigate them.
• Gain practical examples of evaluation setups across NLP tasks.