Natural Language Processing & Audio (incl. Generative AI NLP)
10 talks from the 2026 edition.
-
Do you know how well your model is doing? Evaluate your LLMs ▶ Recording 📝 Transcript
Cheuk Ting Ho
Large Language Models (LLMs) are becoming central to modern applications, yet effectively evaluating their performance remains a significant challenge. How do you objectively compare different models, benchmark the...
-
Don’t call your LLM too often! How to build your dialog graph with confidence and sleep at night. ▶ Recording 📝 Transcript
Evgeniya Ovchinnikova, Andrei Beliankou
Keywords: **Explainable AI, enhanced RAG, GraphRAG, LLMOps, dialog system evaluation.** Designing reliable dialog flows for LLM-based systems remains challenging once conversations require branching, correction, or...
-
From Ticket to Draft: How Munich Automates Citizen Inquiries with AI ▶ Recording 📝 Transcript
Leon Lukas
The City of Munich is modernizing its communication: With the transition to the Zammad ticketing system, there is a unique opportunity to not only manage citizen inquiries but to proactively process them using...
-
It Works on My Machine: Why LLM Apps Fail Users (Not Tests) ▶ Recording 📝 Transcript
Thomas Prexl, Frank Rust
LLM applications frequently pass tests but fail users in production. This talk examines the gap between evaluation metrics and user experience through three lenses: **Expectations** (what "working" means to users),...
-
Making bad CLIs fun with Small Language Models ▶ Recording 📝 Transcript
Moritz Bauer
Command Line Interfaces (CLIs) offer an efficient and powerful way to interact with software, but poorly designed interfaces can be incredibly frustrating. Complicated parameter names and unconventional formats can...
-
Simplifying RAG Document Pipelines with Multimodal Embeddings ▶ Recording 📝 Transcript
Arne Grobrügge
In RAG-based systems, the main challenge is often not tuning the LLM itself, but making documents available in a form that can be retrieved reliably. In enterprise settings, the dominant input format is still PDF,...
-
Small Language Models for Tool Calling Are Better Than You Think ▶ Recording 📝 Transcript
Gabi Kadlecova
Large language models have been widely used in tool-calling workflows thanks to their strong performance in generating appropriate function calls. However, due to their size and cost, they are inaccessible to...
-
Tracking Knowledge Diversity in LLM-Generated Responses. ▶ Recording 📝 Transcript
Sarah Masud
As large language models (LLMs)-powered “AI highlights” become the first information people see on the Web, a key question arises: how much variety and perspective do these systems actually deliver for...
-
Vibe NLP for Applied NLP ▶ Recording 📝 Transcript
Ines Montani
One of the hardest parts of applied NLP has always been breaking down complex business problems into machine learning components. It's so hard because it requires domain expertise and reasoning about the specific use...
-
What Breaks When Automatic Speech Recognition Systems Go Multilingual ▶ Recording 📝 Transcript
Rashmi Nagpal
Building machine learning models for audio deepfake detection seems straightforward until datasets span multiple languages, such as Hindi, Korean, Mandarin, and German. In practice, multilingual Automatic Speech...