HILDA 2025

@SIGMODConf @hildaworkshop is also coming to #Berlin, #Germany! Call for Papers: hilda.io/2025/. Submissions deadline is April 7, 2025. #HILDA2025 #SIGMOD25 #SIGMOD2025

Still working on your @hildaworkshop @SIGMODConf submissions? We *extended* the submission *deadline* by a week! New submission deadline:  April 14, 2025 AOE More details here: hilda.io/2025/

It's been 10 years since @hildaworkshop started, centering around humans in #Data pipelines! We've joined forces with @isj_ais to offer a Special Issue to share ideas about Human-in-the-loop Data and reflect on how the field has progressed over the years: tinyurl.com/SIHilda

Thanks again for making magic happen @shraga_roee, @BehroozOmidvar and Jean-Daniel Fekete. We'll be back😉

We had two inspiring keynotes by @tim_kraska and Renée J. Miller and an enthusiastic discussion about the role of #Humans and #LLMs in #industry including @raghurwi (@Microsoft), Xin Luna Dong (@Meta), @HadasKotek (@Apple), @tim_kraska (@awscloud) and Fatma Ozcan (@Google). 2/2

It was a true pleasure organizing @hildaworkshop @SIGMODConf. I would like to thank my amazing co-chairs @kexinrong, @BehroozOmidvar, and Jean-Daniel Fekete and to all attendees, authors and mentors who made the workshop a success. 📣 Proceedings at lnkd.in/eG9mi4Wy 1/2

This concludes the #HILDA2024 workshop. We extend our heartfelt gratitude to our keynote speakers, panelists, and all presenters for their invaluable contributions. It has been a fantastic experience sharing this time with all of you. Thank you! #SIGMOD2024

Last presentation in #HILDA2024: Causal Dataset Discovery with Large Language Models, remotely presented by Junfei Liu, Shaotong Sun and Fatemeh Nargesian

Our next presentation in #HILDA2024 is titled “Cocoon: Semantic Table Profiling Using Large Language Models” remotely presented by Zezhou Huang, Eugene Wu. #SIGMOD2024

CopycHats is an #LLM-based agent that performs #schemamatching just like humans, allowing us to test revolving doors research questions that we cannot with humans. @SolomonMatan presented this work, co-authored with Bar Genossar and @avigalgal as part of #hilda2024 (#SIGMOD).

Our next presentation in #HILDA2024 is titled “Pipe(line) Dreams: Fully Automated End-to-End Analysis and Visualization” by Cole Beasley and Azza Abouzied. #SIGMOD2024

Time for the third presentation in our last session in #HILDA2024: “LLMs as an Interactive Database Interface for Designing Large Queries” by Yilin Li and Deddy Jobson. #SIGMOD2024

The next presentation in #HILDA2024 is titled “CopycHats: Question Sequencing with Artificial Agents” by Matan Solomon, Bar Genossar, and Avigdor Gal. #SIGMOD2024

We start our last session in #HILDA2024 by the presentation titled “A Diagram Unifying ER and Data Flow Notation For Data Integration and Transformations For Data Science Collaborations” by Robin Varghese, Nguyen Phan, Wojciech Macyna, and Carlos Ordonez. #SIGMOD2024

We have the presentation in #HILDA2024 by Benjamin Hättasch and Carsten Binnig, titled “More of that, please: Domain Adaptation of Information Extraction through Examples & Feedback”

We move to the third presentation of the afternoon session in #HILDA2024: Drag, Drop, Merge: A Tool for Streamlining Integration of Longitudinal Survey Instruments, presented by P. Pokharel, J. Lee, O. Kennedy, J. Good, M. Markatou, A. Talal, and R. Mukhopadhyay

Next presentation in #HILDA2024: Key Insights from a Feature Discovery Use-Case Study, by Andra Ionescu, Zeger Mouw, Efthimia Aivaloglou, Asterios Katsifodimos

Next up in #HILDA2024: “It Took Longer than I was Expecting:” Why is Dataset Search Still so Hard? Presented by Madelon Hulsebos, Wenjing Lin, Shreya Shankar, and Aditya Parameswaran

Our second keynote at HILDA 2024 just started. Renné Miller giving a talk titled “Semantic Benchmark Generation: Can LLMs Generate Better Benchmarks than Humans?”

#LLMs and #HILDA panel starting now @hildaworkshop @SIGMODConf featuring @tim_kraska @HadasKotek @raghurwi, Xin Luna Dong and Fatma Ozcan