iiinova — where your digital self keeps evolving

Madelon Hulsebos @madelonhulsebos.bsky.social · 28/09/2026

Thank you for hosting me! I really enjoyed the discussions with the audience, and throughout my visit at BIFOLD!

Madelon Hulsebos @madelonhulsebos.bsky.social · 09/09/2026

We offer fresh definitions, literature reviews, visions, and rich overviews+analyses of OpenTI systems and benchmarks across communities. Definitely a treasure trove :). Hope you appreciate our write-ups! - Website: open-tabular-insight-extraction.github.io - Paper: arxiv.org/pdf/2609.07629

arxiv.org

000

Madelon Hulsebos @madelonhulsebos.bsky.social · 09/09/2026

In pursuit of democratizing insights from tabular data I’m pleased to share a paper led by @daniel-gomm.bsky.social on where we stand and where we should go in Open Tabular Insight Extraction: the task of serving analytical insight needs over table collections to those unfamiliar with its contents.

121

Madelon Hulsebos @madelonhulsebos.bsky.social · 09/09/2026

000

Reposted by Madelon Hulsebos

ELLIS @ellis.eu · 23/02/2026

💬 Webinar Series 'From Molecules to Models' - today with @madelonhulsebos.bsky.social 🇳🇱 on 'What AI is leaving on the table: Towards democratizing insights from tabular data'. 📅 Mon, Feb 23 🕓 16:00-17:00 CET 🔗 Registration: bit.ly/4ash9gn ℹ️ More info: bit.ly/47Qclim

AI for Good Webinar Series 'From Molecules to Models' - today with Madelon Hulsebos on 'What AI is leaving on the table: Towards democratizing insights from tabular data'.

0111

Madelon Hulsebos @madelonhulsebos.bsky.social · 22/01/2026

People can join also online! Check the page for the link.

000

Madelon Hulsebos @madelonhulsebos.bsky.social · 22/01/2026

Join the TRL Seminar tomorrow for talks on query ambiguity in open-domain data analysis @daniel-gomm.bsky.social, the SQaLE dataset for training text-to-SQL models @cowolff.bsky.social, and pattern/rule inference from tabular data @erkankarabulut.bsky.social. Info: trl-lab.github.io/trl-seminar/

trl-lab.github.io

TRL Seminar | TRL Lab

153

Madelon Hulsebos @madelonhulsebos.bsky.social · 06/01/2026

Today I wrote an elaborate email, which I hadn't done for a while. I realize that I start to enjoy crafting nice and authentic stories, word by word, now that most texts are LLM'd. The LLM era makes me more creative and thoughtful about my daily writing than before. Here's to more writing in 2026!

030

Madelon Hulsebos @madelonhulsebos.bsky.social · 04/12/2025

- Besides the workshop, I’m really looking forward to other great talks from the tabular community during the main program eg on TabArena, ConTexTab, the keynotes/panels as well as other great work presented there. Generally it’ll be amazing to connect with the European AI crowd!

000

Madelon Hulsebos @madelonhulsebos.bsky.social · 04/12/2025

- The workshop ends with a reception for the vibrant tabular AI community to connect over drinks: can’t wait to catch up with folks! Really grateful to our sponsors for accommodating this: SAP, Prior Labs, and ELLIS unit Amsterdam 🙏.

lnkd.in

This link will take you to a page that’s not on LinkedIn

100

Madelon Hulsebos @madelonhulsebos.bsky.social · 04/12/2025

- Our contributions: 1) a take on ambiguity in NL-based tabular data analysis, spotlight+poster: arxiv.org/abs/2511.04584, 2) SQaLe: the largest text-to-SQL dataset grounded in real schemas, poster: openreview.net/forum?id=6Ps..., 3) my surprise keynote on our work & reflection on the community :)

trl-lab.github.io

TRL Lab

120

Madelon Hulsebos @madelonhulsebos.bsky.social · 04/12/2025

- We’re organizing the AI for Tabular Data workshop w/ 3 keynotes, 9 spotlights, and 48 fresh papers in 2 poster sessions ✨ Excited about the great directions and quality of the work in this community! Papers & program at sites.google.com/view/eurips2.... Join us Sat 6 Dec at the Univ of Copenhagen!

lnkd.in

This link will take you to a page that’s not on LinkedIn

110

Madelon Hulsebos @madelonhulsebos.bsky.social · 04/12/2025

I’m at EurIPS in Copenhagen this week! Great seeing the AI crowd come together in Europe 🤩. Would love to chat with people about 1) AI for tabular data, 2) new collaborations (prospective students, phd visitors, peers from other labs/disciplines), 3) the future of AI in Europe. Some highlights:

140

Madelon Hulsebos @madelonhulsebos.bsky.social · 24/11/2025

Looking forward to hosting Irina Saparina (Univ. of Edinburgh, saparina.github.io) this Friday for a talk in the TRL Seminar on "From Implicit Bias to Explicit Choice: Handling Ambiguity in Text-to-SQL Parsing" 👀. 📆 Fri 28 Nov 4-5pm CEST 📍 CWI lobby 3:50pm or Zoom 👇 trl-lab.github.io/trl-seminar

021

Madelon Hulsebos @madelonhulsebos.bsky.social · 20/11/2025

Paper: openreview.net/pdf?id=6PsKD... Dataset on HuggingFace: huggingface.co/datasets/trl... Blogpost on HuggingFace: huggingface.co/blog/cwolff/...

lnkd.in

This link will take you to a page that’s not on LinkedIn

010

Madelon Hulsebos @madelonhulsebos.bsky.social · 20/11/2025

Really great effort that is led by @cowolff.bsky.social in colab with @daniel-gomm.bsky.social, and will be presented at the AI for Tabular Data workshop at EurIPS on 6 Dec! Stay tuned for our research on insight extraction from tabular data (also beyond text-to-SQL).

100

Madelon Hulsebos @madelonhulsebos.bsky.social · 20/11/2025

Excited to introducd the SQaLe dataset for text-to-SQL training/tuning at scale. SQaLe is the first large-scale text-to-SQL dataset grounded in real schemas and covers a broad range of realistic queries (eg # joins, operations). SQaLe provides 517K high-quality question/schema/query triples 🤩.

184

Madelon Hulsebos @madelonhulsebos.bsky.social · 17/11/2025

We consider NL tabular query ambiguity through the lens of cooperative interaction. Read more about the insights and implications in the paper led by Daniel, which will be presented at the EurIPS workshop on AI for Tabular Data! arxiv.org/pdf/2511.04584 Really enjoyed this reflection exercise 🙂

arxiv.org

030

Madelon Hulsebos @madelonhulsebos.bsky.social · 17/11/2025

For a long time, we reviewed and debated properties of queries in tabular QA datasets and practice, particularly in an “open-domain” context. Expecting “platonic queries”, map to necessary and sufficient data items and only the exact operational procedure to address the query intent, is unrealistic.

120

Madelon Hulsebos @madelonhulsebos.bsky.social · 17/11/2025

Are We Asking the Right Questions? With @daniel-gomm.bsky.social and @cowolff.bsky.social we wrote a reflection on ambiguity in natural language queries for tabular data analysis: What queries should we expect, facilitate? On what should tabular data analysis systems be evaluated, and how? See thrd

142

Madelon Hulsebos @madelonhulsebos.bsky.social · 01/10/2025

I'm hiring PhDs through the ELLIS PhD program for research on table representation learning to democratize insights from tabular data! Info: trl-lab.github.io/open-positio... Apply: apply.ellis.eu (31 Oct) Join us in beautiful Amsterdam at @cwi-amsterdam.bsky.social & @ellisamsterdam.bsky.social ✨

apply.ellis.eu

ELLIS Application System

051

Madelon Hulsebos @madelonhulsebos.bsky.social · 23/09/2025

This exciting workshop is organized by @effylix.bsky.social, @lennartpurucker.bsky.social, Peter Baile Chen, Frank Hutter and me. With talks by Marine Le Morvan (Inria), Floris Geerts (University of Antwerp) and @akhtarmubashara.bsky.social (ETH Zurich), and more TBA. We hope to meet you there!!

000

Madelon Hulsebos @madelonhulsebos.bsky.social · 23/09/2025

🚀 Excited to announce the AI for Tabular Data workshop at EurIPS 2025 in Copenhagen! CfP: sites.google.com/view/eurips2... (papers due 20 Oct) Join us @euripsconf.bsky.social to discuss neural tabular models and systems for predictive ML, tabular reasoning and retrieval, table synthesis and more ✨

Announcement for the EurIPS'25 Workshop on AI for Tabular Data. More information about the workshop can be found at: https://sites.google.com/view/eurips25-ai-td/home.

173

Madelon Hulsebos @madelonhulsebos.bsky.social · 01/09/2025

Also hope attendees will enjoy the tutorial program, which I helped compile this year, with exciting tutorials on topics such as vector search, data discovery, graph databases, AI and relational data! Full list at vldb.org/2025/?papers...

vldb.org

VLDB 2025 - Industrial Track Papers

List of accepted industrial track papers.

010

Madelon Hulsebos @madelonhulsebos.bsky.social · 01/09/2025

Off to London 🇬🇧 for @vldb.bsky.social! Looking forward to the panel discussion on neural models and tabular data Tue 10:45 🔥. I’ll share my thoughts on the state of affairs, promising paradigms, and future directions for TRL. Will share my input and some take-aways of the discussions post conf.

140

Madelon Hulsebos @madelonhulsebos.bsky.social · 30/07/2025

We show that metrics like sacrebleu and bertscore aren't fit for tabular QA eval of LLMs as scores are inseparable. We also find a large gap between multiple-choice eval as in TQA-Bench and an LLM-judge which aligns with human annotation. Bottomline: LLMs aren't robust for real-world multi-table QA

000

Madelon Hulsebos @madelonhulsebos.bsky.social · 30/07/2025

In our contribution led by @cowolff.bsky.social from the TRL Lab (trl-lab.github.io) we wondered: how well do LLMs reason over tabular data, really? We find that LLMs don't ack nor handle tables with disturbances (eg missing vals or duplicates) necessitating explicit prompting or cleaning pipelines.

trl-lab.github.io

TRL Lab

110

Madelon Hulsebos @madelonhulsebos.bsky.social · 30/07/2025

The full program of the workshop is at: table-representation-learning.github.io/ACL2025/. Besides excellent contributed work (proceedings: aclanthology.org/2025.trl-1.0...), we'll have invited talks by Dan Roth, Tao Yu, Edward Choi and Julian Eisenschlos!

arxiv.org

How well do LLMs reason over tabular data, really?

Large Language Models (LLMs) excel in natural language tasks, but less is known about their reasoning capabilities over tabular data. Prior analyses devise evaluation strategies that poorly reflect an...

100

Madelon Hulsebos @madelonhulsebos.bsky.social · 30/07/2025

Excited to be at ACL! Join us at the Table Representation Learning workshop tomorrow in room 2.15 to talk about tables and AI. We also present a paper showing the sensitivity of LLMs in tabular reasoning to e.g. missing vals and duplicates, by @cowolff.bsky.social at 16:50: arxiv.org/abs/2505.07453

163

Reposted by Madelon Hulsebos

Cornelius Wolff @cowolff.bsky.social · 25/07/2025

The paper's called: "How well do LLMs reason over tabular data, really?" 📊 We dig into two important questions: 1️⃣ Are general-purpose LLMs robust with real-world tables? 2️⃣ How should we actually evaluate them? (2/4)

111

Madelon Hulsebos @madelonhulsebos.bsky.social · 17/07/2025

Very excited about this! Aligns well with my 🇪🇺 focus this year.

050

Reposted by Madelon Hulsebos

Madelon Hulsebos @madelonhulsebos.bsky.social · 16/06/2025

Join us for discussions and talks on data management aspects for end-to-end ML on 27 June at @deem-workshop.bsky.social in Berlin. Keynotes by @pinartozun.bsky.social and @gaelvaroquaux.bsky.social 🤩 Check the full schedule deem-workshop.github.io#schedule & proceedings dl.acm.org/doi/proceedi...

dl.acm.org

Proceedings of the Workshop on Data Management for End-to-End Machine Learning | ACM Conferences

085

Madelon Hulsebos @madelonhulsebos.bsky.social · 26/06/2025

Very interesting! I’ve seen synthetic data, with certain patterns (eg TabPFN with SCMs), come real far, but not entirely random compositions of tokens. Do you understand or have an hypothesis for what leads to this observation?

000

Reposted by Madelon Hulsebos

Lennart Purucker @lennartpurucker.bsky.social · 23/06/2025

🚨What is SOTA on tabular data, really? We are excited to announce 𝗧𝗮𝗯𝗔𝗿𝗲𝗻𝗮, a living benchmark for machine learning on IID tabular data with: 📊 an online leaderboard (submit!) 📑 carefully curated datasets 📈 strong tree-based, deep learning, and foundation models 🧵

1178

Reposted by Madelon Hulsebos

Madelon Hulsebos @madelonhulsebos.bsky.social · 05/06/2025

Let’s collaborate on democratizing insights from tabular data in Amsterdam! ✨ PhD directions: 1) fundamental techniques for tabular foundation models, 2) reliable mechanisms for AI-powered tabular data analysis. Sharing w/ friends appreciated! ⬇️

233

Madelon Hulsebos @madelonhulsebos.bsky.social · 16/06/2025

dl.acm.org

Proceedings of the Workshop on Data Management for End-to-End Machine Learning | ACM Conferences

085

Madelon Hulsebos @madelonhulsebos.bsky.social · 09/06/2025

Absolutely! Please send me an email then we can arrange a chat :)

110

Madelon Hulsebos @madelonhulsebos.bsky.social · 05/06/2025

233

Reposted by Madelon Hulsebos

ELLIS @ellis.eu · 05/06/2025

🏹 Job alert: 2 fully-funded PhD Positions at Table Representation Learning Lab - @ellisamsterdam.bsky.social‬ 📍 Amsterdam 🇳🇱 📅 Apply by June 30 🔗 More info: bit.ly/4519pj1

bit.ly

Open positions | TRL Lab

013

Reposted by Madelon Hulsebos

Cornelius Wolff @cowolff.bsky.social · 28/05/2025

"Can LLMs really reason over tabular data, really?" That’s the title and central question of my first paper in my new role as a PhD student, which has been accepted to the 4th Table Representation Learning Workshop @ ACL 2025! arxiv.org/pdf/2505.07453 🧵Here’s what we found:

121

Reposted by Madelon Hulsebos

Madelon Hulsebos @madelonhulsebos.bsky.social · 22/05/2025

Eager to contribute to democratizing insights from tabular data? We have 2 new PhD openings! ✨ 1) Fundamental Techniques in Table Representation Learning 2) Reliable AI-powered Tabular Data Analysis Systems ⏰ Apply by: 30 June 2025 📅 Start: Fall/Winter 2025 🔗 Info: trl-lab.github.io/open-positions

trl-lab.github.io

Open positions | TRL Lab

043

Madelon Hulsebos @madelonhulsebos.bsky.social · 22/05/2025

trl-lab.github.io

Open positions | TRL Lab

043

Madelon Hulsebos @madelonhulsebos.bsky.social · 18/04/2025

Curious to hear other thoughts on this nice survey. We’ll continue doing this going forward, and everyone is welcome to join: trl-lab.github.io/trl-reading-.... Also for the monthly seminar btw ✨

trl-lab.github.io

TRL reading group | TRL Lab

030

Madelon Hulsebos @madelonhulsebos.bsky.social · 17/04/2025

We're currently finalizing some quite detailed insights on this (can share the paper next week, and will send some plots on DM). TLDR is that an LLM-as-a-judge is best, for now, for evaluating free-form text against precise answers. Methods like sacrebleu and bert-score do not give a clear signal...

120

Madelon Hulsebos @madelonhulsebos.bsky.social · 17/04/2025

This is also an issue for evaluation.. one approach could be to make a second LLM call to extract the concise answer / value from generated text.

110

Madelon Hulsebos @madelonhulsebos.bsky.social · 11/04/2025

This talk is today, 4-5pm UvA lab42 Amsterdam and Zoom. Looking forward 🤩

010

Reposted by Madelon Hulsebos

Table Representation Learning research @trl-research.bsky.social · 08/04/2025

Good news for authors of submissions to the Table Representation Learning workshop @ ACL: we're extending the deadline a little bit. Papers are due 21 April. No exceptions from there :).

011