Über uns
A group for experienced and aspiring data professionals.
Join our Slack: https://datatalks.club/slack.html
Kommende Veranstaltungen
5
How to Reduce LLM Hallucinations with Wikidata: Hands-On Fact-Checking Using MCP
·OnlineOnlineLLMs are powerful, but they still hallucinate facts, especially when asked about entities, relationships, or claims that require up-to-date or structured knowledge.
In this hands-on workshop, we'll explore how to use Wikidata as a grounding and fact-checking layer for LLMs to reduce hallucinations and make AI systems more reliable.
We'll start with a short introduction to Wikidata and then set up the Wikidata MCP so an LLM can retrieve and verify facts rather than relying solely on its internal memory. This already provides a practical way to ground LLM outputs in verifiable data.
From there, we’ll go beyond LLM-only approaches and build a small experimental fact-checking pipeline. The system combines semantic retrieval, LLM-based reranking, and natural language inference (NLI) to validate claims against evidence in a more controlled and interpretable way.
This workshop focuses on evidence-driven verification pipelines that make LLM's reasoning steps explicit and easier to inspect, debug, and improve.
What we'll cover:
- Wikidata as a structured source for factual verification
- Setting up and querying Wikidata using MCP
- Verifying claims with MCP + an LLM
- Moving beyond pure GenAI to evidence-based fact-checking
- Finding relevant Wikidata statements with semantic search
- Ranking candidate evidence with an LLM
- Verifying claims using an NLI model
What you'll leave with
By the end of the workshop, you'll be able to:
- Ground LLM outputs in structured data to reduce hallucinations
- Understand when LLM-only fact-checking is not enough
- Build a small, transparent fact-checking pipeline you can adapt to real projects
About the speaker:
Philippe Saadé is the AI/ML project manager at Wikimedia Deutschland. His current work focuses on making Wikidata accessible to AI application with projects like the Wikidata vector database and the Wikidata Model Context Protocol.
Join our Slack: https://datatalks.club/slack.html
This event is sponsored by Wikimedia54 Teilnehmer
The Future of AI Agents
·OnlineOnlineExploring open source profitability and small language models – Aditya Gautam
Aditya Gautam has built his career at the intersection of AI research, large-scale deployment, and public discourse. With experience at Google, Meta, and leading academic conferences, he works on large language models, AI agents, and responsible AI at scale.
In this episode, Aditya will explore the debates around open-source AI, the economics behind LLMs, and the barriers enterprises face when adopting AI agents. He also shares his perspective on the rise of small language models and what these shifts mean for the future of AI.
We plan to cover:
- Open-source AI: democratization and risks
- The economics of LLMs and the challenge of profitability
- Why enterprises struggle to adopt AI agents in practice
- The role of small language models in efficiency and cost reduction
- Emerging trends in AI research and deployment
About the Guest
Aditya Gautam is an AI expert contributing to the advancement of the field through industrial innovation, academic research, and public discourse. At the core of his work, he designs and builds systems in the domain of Large Language Models (LLMs) and AI Agents. He has successfully led several high-impact applied AI initiatives at Meta, focusing on both enhancing core ranking and recommendation algorithms and successfully architecting, developing, and productionizing state-of-the-art GenAI systems at massive scale.
As an active voice in the Generative AI community, Aditya actively disseminates his expertise on the global stage. He was featured among the best speakers at the Databricks Data + AI Summit 2025 for his talk on "Optimize Cost and User Value Through Model Routing AI Agent." He has published research on LLMs in Information Retrieval and Multi-Agent Systems, and his thought leadership has been featured in major media articles, industry interviews, and AI podcasts. He is a frequent speaker and panelist at premier events and conferences such as Analytics Vidhya. His influence in the academic community is demonstrated by his service as a respected peer reviewer for top-tier venues like NeurIPS, ICML, and AAAI. Aditya holds a Master’s degree from Carnegie Mellon University.
**Join our Slack: https://datatalks.club/slack.html**85 Teilnehmer
Vergangene Veranstaltungen
363
