Reut Yaniv

Evaluating the Performance of LLM-Powered Conversational Reporting at Waze
Reut Yaniv

Abstract

This lecture will cover the evaluation framework of a new LLM-powered conversational reporting feature in Waze. The conversational reporting feature allows users to report traffic incidents (such as crashes, hazards and more) safely while driving, in natural language. The model is designed to understand the type of traffic report users want to make, ask further required clarifications, and submit it accordingly.

Bio

Reut is a data science leader with a 15 year track record of building and scaling data-driven products.

During the last 3.5 years, Reut has led the DS efforts around several domains at Waze including driver reports, city partner data collection, insights surfacing, onboarding, search, monetization, and more, allowing safe rollouts of dozens of new features and ML based tools and capabilities.

Previously, as a director of data science at Natural Intelligence, Reut spearheaded the transition from manual marketing operations to ML-based systems, developing the data infrastructure and leading the development of machine learning-powered marketing optimization products. These initiatives have resulted in a 10% lift in gross profit on a $30M annual marketing budget.

Prior to this, Reut was a data scientist at Agoda, where she owned algorithmic components of a marketing system and implemented new features in a big-data production environment.

Reut holds an MS in data science from the University of Chicago and a BSc in industrial engineering and management (summa cum laude) from Ben-Gurion University.

Agenda

8:45 Reception
9:30 Opening remarks by WiDS TLV ambassadors
9:45 Dr. Mor Geva , Tel Aviv University: “MRI for Large Language Models: Mechanistic Interpretability from Neurons to Attention Heads”
10:15 Panel: “Pioneering Progress: a strategic look at the GenAI revolution and the new role of data scientists“
Shani Gershtein, Melingo
Mirit Elyada Bar, Intuit
Dr. Asi Messica, Lightricks
Moderated by Nitzan Gado, Intuit
10:45 Poster pitches
10:55 Break
11:10 Lightning talks session
12:30 Lunch & poster session
13:30 Roundtable session & poster session
14:30 Roundtable closing
14:40 Shunit Agmon, Technion: “Bridging the Gender Gap in Clinical AI: Temporal Adaptation with TeDi-BERT”
15:00 Shaked Naor Hoffmann, Apartment List: “Building Generative AI Agents for Production: Turning Ideas into Real-World Applications”
15:20 Closing remarks
15:30 The end