talk-data.com talk-data.com

Event

Retrieval, search and knowledge in the age of LLM and Vector Databases

2023-11-07 – 2023-11-07 Meetup Visit website ↗

Activities tracked

2

PLEASE NOTE: Clicking 'attend' does not register you for the event. You will need to register for the event on the link provided below to receive a QR code ticket via email. If you do not have a QR code, you will not be able to attend the event.

👇 Click below to register for this event for FREE 👇 https://datasciencefestival.com/session/retrieval-search-and-knowledge-in-the-age-of-llm-and-vector-databases/

Join us in London for our next in-person meet-up in partnership with Digitas on Tuesday 7th November 2023. A free evening of tech talks, a chance to network with the community with refreshments and food provided.

📆 Date: Tuesday 7th November 2023 ⏰ Time: 6:00 pm - 9:00 pm GMT 📍 Location: Digitas – 40 Chancery Ln, London WC2A 1JA – Ground floor reception

Talk 1: Are all the paths to AGI passing through the Transformers station? (Louis Vainqueur – Partner, Data Science @ Digitas)

Since the release of ChatGPT late last year, the world has finally embraced vector embeddings and many organisations (from hedge funds to giant retailers) have been experimenting with vector databases. This is because vector embeddings, a component at the heart of large language models, open-up the ability to not only compress information but also to drastically transform search and knowledge retrieval.

In this session we will put a spotlight on the embedding revolution that has taken over natural language processing, computer vision, network science and explain how enterprises can build better systems to understand, interact with, and sell to their customers.

Talk 2: Causal Modelling Agents: Augmenting Causal Discovery with LLMs (Ayodeji Ijishakin – PhD Candidate, University College London Ahmed Abdulaal - PhD Candidate, University College London)

Scientific discovery hinges on the effective integration of metadata, which refers to a set of 'cognitive' operations such as determining what information is relevant for inquiry, and data, which encompasses physical operations such as observation and experimentation. This talk introduces the Causal Modelling Agent (CMA), a novel framework that synergizes the metadata-based reasoning capabilities of Large Language Models (LLMs) with the data-driven modelling of Deep Structural Causal Models (DSCMs) for the task of causal discovery. We evaluate the CMA's performance on a number of benchmarks, as well as on the real-world task of modelling the clinical and radiological phenotype of Alzheimer's Disease (AD). Our experimental results indicate that the CMA can outperform previous data-driven or metadata-driven approaches to causal discovery. In our real-world application, we use the CMA to derive new insights into the causal relationships among biomarkers of AD.

Full speaker abstracts and bios can be found here.

Schedule: 6:00 PM - Doors open - food, drinks and networking. 6:30 PM - Intro. 6:35 PM - Talk session Louis, followed by Q&A. 7:15 PM - Short comfort break. 7:25 PM - Talk session Ayodeji and Ahmed, followed by Q&A. 8:05 PM - Drinks and networking. 9:00 PM - Close.

Food and drinks are included.

PLEASE NOTE: Clicking 'attend' does not register you for the event. You will need to register for the event on the link provided below to receive a QR code ticket via email. If you do not have a QR code, you will not be able to attend the event. 👇 Click below to register for this event for FREE 👇 https://datasciencefestival.com/session/retrieval-search-and-knowledge-in-the-age-of-llm-and-vector-databases/

Sessions & talks

Showing 1–2 of 2 · Newest first

Search within this event →

Are all the paths to AGI passing through the Transformers station?

talk
louis vainqueur (Digitas)
vector embeddings vector databases large language models (llms)

Since the release of ChatGPT late last year, the world has finally embraced vector embeddings and many organisations (from hedge funds to giant retailers) have been experimenting with vector databases. This is because vector embeddings, a component at the heart of large language models, open-up the ability to not only compress information but also to drastically transform search and knowledge retrieval. In this session we will put a spotlight on the embedding revolution that has taken over natural language processing, computer vision, network science and explain how enterprises can build better systems to understand, interact with, and sell to their customers.

Causal Modelling Agents: Augmenting Causal Discovery with LLMs

talk
ayodeji ijishakin (University College London) , ahmed abdulaal (University College London)
large language models (llms) causal modelling agents (cma) causal discovery

Scientific discovery hinges on the effective integration of metadata, which refers to a set of 'cognitive' operations such as determining what information is relevant for inquiry, and data, which encompasses physical operations such as observation and experimentation. This talk introduces the Causal Modelling Agent (CMA), a novel framework that synergizes the metadata-based reasoning capabilities of Large Language Models (LLMs) with the data-driven modelling of Deep Structural Causal Models (DSCMs) for the task of causal discovery. We evaluate the CMA's performance on a number of benchmarks, as well as on the real-world task of modelling the clinical and radiological phenotype of Alzheimer's Disease (AD). Our experimental results indicate that the CMA can outperform previous data-driven or metadata-driven approaches to causal discovery. In our real-world application, we use the CMA to derive new insights into the causal relationships among biomarkers of AD.