LLM
-
Beyond the demo: Why agentic evaluation matters
Agentic systems powered by LLMs can be incredibly impressive in demos. With a few well-crafted prompts, they can demonstrate reasoning, calling tools, and solving complex tasks [1]. Demos are effective at showcasing what’s possible. Production environments, however, are where those capabilities are tested at scale and under real-world conditions. The same agent that performs perfectly…
-
How RecSys & LLMs Will Converge: Architecture of Hybrid RecoAgents
Recommender systems have become critical infrastructure in commerce. Their role is not only to surface relevant items but also to shape how users explore, compare, and decide. Improvements in recommendation translate directly into superior business outcomes: higher engagement, more conversions, stronger loyalty, and more efficient allocation of marketing budgets. Over the last couple of years,…
-
Our participation in the International Conference on Machine Learning 2024
The 41st edition of the International Conference on Machine Learning (ICML) took place from July 21 to July 27, 2024, at the Messe Wien Exhibition Congress Center in Vienna, Austria. This prestigious event, known for showcasing groundbreaking research in machine learning, artificial intelligence, statistics, and data science, adopted a hybrid format this year, allowing both…
-
Insights and Highlights from CommitConf’24
CommitConf 2024 took place one more time this year in Madrid, from April 19 to April 20, drawing over 1000 participants and hosting more than 80 speakers. The event provided an excellent platform for delving into topics such as software architecture, Machine Learning, Developer Experience, and real-world experiences. This two-day conference is one of the…
-
Our experience at EACL’24
As we gathered at the 2024 edition of the European Chapter of the Association for Computational Linguistics (EACL), we were all eager to see where the community’s research was headed after a whirlwind year of Large Language Model (LLM) breakthroughs. Although one could have thought that ChatGPT was the answer to all our questions, we…