Papers
arxiv:2604.09237

ScheMatiQ: From Research Question to Structured Data through Interactive Schema Discovery

Published on Apr 10
· Submitted by
Eliya Habba
on Apr 13
Authors:
,
,
,
,
,

Abstract

ScheMatiQ uses large language model calls to automatically generate annotation schemas and structured databases from document collections, supporting domain-specific analysis in law and computational biology through an interactive web interface.

AI-generated summary

Many disciplines pose natural-language research questions over large document collections whose answers typically require structured evidence, traditionally obtained by manually designing an annotation schema and exhaustively labeling the corpus, a slow and error-prone process. We introduce ScheMatiQ, which leverages calls to a backbone LLM to take a question and a corpus to produce a schema and a grounded database, with a web interface that lets steer and revise the extraction. In collaboration with domain experts, we show that ScheMatiQ yields outputs that support real-world analysis in law and computational biology. We release ScheMatiQ as open source with a public web interface, and invite experts across disciplines to use it with their own data. All resources, including the website, source code, and demonstration video, are available at: www.ScheMatiQ-ai.com

Community

Paper submitter

Many disciplines pose research questions over large document collections that require structured evidence, traditionally obtained through slow, manual annotation. ScheMatiQ takes a natural-language research question and a document collection, and uses LLM calls to discover the observation unit, induce a query-driven schema, and extract a grounded structured database. An interactive web interface lets domain experts steer and revise the process at every stage. In evaluations with experts in law and computational biology, ScheMatiQ recovers the vast majority of manually curated schema fields while surfacing new ones rated highly relevant. Open source with a public web interface at https://www.schematiq-ai.com/

Learn to become human first then maybe do research , research community is in full independence of criminal 'research' , keep that 'research' for yourself, justice come first then we talk about 'research', we are human before being researcher, So anything that a person produce related to appartheid and criminals is of none worth and discarded without consideration, absolute zero consideration. The country is for Muslims , we welcomed you when you are perscuted , yet look at your actions, absolute corruption , zionism is at its last breath , you have either to denounce any tie to the appartheid so when day comes justice is served and thus you will be getting (By Allah) what we were promised by Allah and prophet, in this life before the hereafter, even the stone and tree then speaks to expose criminal so they get their judgement.

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2604.09237
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2604.09237 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2604.09237 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2604.09237 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.