Daniel Gomm
@daniel-gomm.bsky.social
PhD Student at CWI, Amsterdam
Researching at the intersection of structured data, gen AI and IR
Researching at the intersection of structured data, gen AI and IR
Reposted by Daniel Gomm
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 🤩.
SQaLe provides 517K high-quality question/schema/query triples 🤩.
November 20, 2025 at 10:59 AM
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 🤩.
SQaLe provides 517K high-quality question/schema/query triples 🤩.
Reposted by Daniel Gomm
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
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
November 17, 2025 at 3:15 PM
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
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
Reposted by Daniel Gomm
Excited to share the new monthly Table Representation Learning (TRL) Seminar under the ELLIS Amsterdam TRL research theme! To recur every 2nd Friday.
Who: Marine Le Morvan, Inria (in-person)
When: Friday 11 April 4-5pm (+drinks)
Where: L3.36 Lab42 Science Park / Zoom
trl-lab.github.io/trl-seminar/
Who: Marine Le Morvan, Inria (in-person)
When: Friday 11 April 4-5pm (+drinks)
Where: L3.36 Lab42 Science Park / Zoom
trl-lab.github.io/trl-seminar/
April 2, 2025 at 9:42 AM
Excited to share the new monthly Table Representation Learning (TRL) Seminar under the ELLIS Amsterdam TRL research theme! To recur every 2nd Friday.
Who: Marine Le Morvan, Inria (in-person)
When: Friday 11 April 4-5pm (+drinks)
Where: L3.36 Lab42 Science Park / Zoom
trl-lab.github.io/trl-seminar/
Who: Marine Le Morvan, Inria (in-person)
When: Friday 11 April 4-5pm (+drinks)
Where: L3.36 Lab42 Science Park / Zoom
trl-lab.github.io/trl-seminar/
How can we make LLMs understand tabular data better? My latest blog post compares table serialization techniques using the Table Serialization Kitchen, showing large gaps between approaches in table retrieval settings.
daniel-gomm.github.io/blog/2025/Ta...
daniel-gomm.github.io/blog/2025/Ta...
Table Serialization Kitchen - A Recipe for Better LLM Performance on Tabular Data | Daniel Gomm
This blog post explores table serializations and their impact on downstream tasks using the Table Serialization Kitchen.
daniel-gomm.github.io
March 5, 2025 at 2:31 PM
How can we make LLMs understand tabular data better? My latest blog post compares table serialization techniques using the Table Serialization Kitchen, showing large gaps between approaches in table retrieval settings.
daniel-gomm.github.io/blog/2025/Ta...
daniel-gomm.github.io/blog/2025/Ta...