> Markdown version of [/events/world-congress-2025/sessions/734-adding-knowledge-to](https://www.wearedevelopers.com/events/world-congress-2025/sessions/734-adding-knowledge-to). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# Adding knowledge to open-source LLMs


- **Date:** Friday, Jul 11, 2025
- **Time:** 09:40–10:10 (30 min)
- **Room:** Stage 2
- **Event:** World Congress 2025

## Recording

[Watch recording](https://www.wearedevelopers.com/videos/1522-adding-knowledge-to-open-source-llms)

## Description

While Large Language Models are remarkably powerful, their knowledge is typically limited to the data available during training. This makes their applications challenging when business contexts, or cultural nuances change or are not well represented in their original training data. In many cases, in-context learning techniques such as retrieval-augmented generation (RAG) can help to bridge this gap by providing models with relevant information at runtime. However, when a model lacks foundational understanding of domain-specific knowledge, use case, or local cultural context, even advanced retrieval methods may fail.
In this session, NVIDIA experts will explain how to enrich language models with new knowledge, expanding their capabilities in specialized business, engineering, or scientific domains, and adjusting adaptation to new languages, cultures, and values.


## Speakers

### [Harshita Seth](https://www.wearedevelopers.com/@harshita-seth)

Senior Solution Architect at Nvidia
### [Sergio Perez](https://www.wearedevelopers.com/@sergio-perez)

Solution Architect at NVIDIA


## Related talks at this congress

- [ Model Compression Techniques for Efficient LLM Deployment](https://www.wearedevelopers.com/events/world-congress-2025/sessions/811-model-compression) — Harshita Seth, Lavinia Ghita, Sergio Perez, Ziv Ilan
- [Breaking Language Barriers: GPU-Accelerated Corpus Curation for LLM Training/Customization](https://www.wearedevelopers.com/events/world-congress-2025/sessions/812-breaking-language) — Miguel Martínez, Roman
- [Self-Hosted LLMs: From Zero to Inference](https://www.wearedevelopers.com/events/world-congress-2025/sessions/625-self-hosted-llms) — Cedric Clyburn, Roberto Carratalá
- [Inside the Mind of an LLM](https://www.wearedevelopers.com/events/world-congress-2025/sessions/831-inside-the-mind-of) — Emanuele Fabbiani