Unstructured Data

Follow this topic Ask about this topic

Momentum

11 papers in the last four weeks, up 175% on the four weeks before. 0.1% of all new papers.

Jul 6Week of Sep 21

Latest papers 42

All topics

Identifying ODEs from Unstructured Data with Causal Representation Learning
Sep 29, 2026Alessandro Trenta, Riccardo Massidda, Davide Bacciu +1Ordinary Differential Equations Causal Representation Learning
Department of Computer Science University of Pisa · Saarland Informatics Campus Saarland University & University of Amsterdam
JevOut: Natural Context Can Flip Decision Models
Sep 24, 2026Zixiang XuDecisions Contextual Reasoning
University of Southern California
Post-Training Leaves Behavioral Shadows on Unrelated Decisions
Sep 24, 2026Ziyang Zhang, Yubin Jing, Yuanhao Zeng +3Post-Training Agent Behavior Modeling
Peking University · Georgia Institute of Technology · ShanghaiTech University +2
UniDataAgent: An Ontology-Grounded Agent for Enterprise Question-to-Report Automation
Sep 23, 2026Yutai Duan, Yahui Zhao, Zhangti Li +5Data Science Agents Ontology
China Unicom Software Research Institute Beijing, China
Domain-Adaptive Pretraining Enhances Water Treatment Semantic Representation for Large-Scale Structured Literature Mining
Sep 22, 2026Mudi Zhai, Ruihong Qiu, Qingyun Zeng +3Information Extraction Bert-Based Models
UNSW Water Research Centre, School of Civil and Environmental Engineering, The University of New South Wales, Sydney, NSW 2052, Australia · School of Electrical Engineering and Computer Science, The University of Queensland, Brisbane, QLD 4072, Australia · Microsoft Copilot Studio AI, Redmond, WA 98052, United States +2
Q&A on Any Spreadsheet Requires Interpreting Its Grid Structure
Sep 17, 2026Zofia SmoleńSpreadsheets Chunk
Systems Research Institute, Polish Academy of Sciences Warsaw, Poland
Efficiently Linking Unstructured Data for Multi-step Reasoning
Sep 16, 2026Jiaming Liang, Haydn Jones, Jacob R. Gardner +2Unstructured Data Precision Recall
University of Pennsylvania Philadelphia, PA, USA
Quantifying Organizational Environmental Action from Web Data and Large Language Models
Sep 15, 2026Quinn Reynolds, Daniel Shore, Vianey Leos Barajas +2Unstructured Data Organizational Research
Department of Statistical Sciences, University of Toronto · School of the Environment, University of Toronto
Beyond the Name: Demographic Leakage in De-Identified Résumés and Evaluation Artifacts in LLM Bias Audits
Sep 15, 2026Qiangju Chen, Yang XiaoLarge Language Model Bias Data Leakage
Macquarie University · The University of Melbourne
Automated Event Log Generation from Unstructured Text Using Finetuned LLMs
Sep 1, 2026Maximilian Seeth, Gabriel Marques Tavares, Daniel SchusterUnstructured Data Large Language Model Pipelines
LMU Munich, Germany · University of Mannheim, Germany
Verifiable Disaster Storylines and Causal Knowledge Graphs: A Citation-Grounded Pipeline from Heterogeneous Humanitarian Sources
Sep 1, 2026Ivan Decostanzi, Michele Ronco, Sergio Consoli +8Disaster Response Humanitarian Reports
ISI Foundation · Turin, Italy · European Commission, Joint Research Centre (JRC) +4
Token-Efficient Data Reasoning Agents via Adaptive Structuring of Unstructured Data
Aug 31, 2026Milad Rezaei Hajidehi, Qitong Wang, Stratos IdreosData Science Agents Unstructured Data
Harvard University · Cambridge, Massachusetts, USA
Prompts in the Wild: A Large Analyzed Collection of Transactional Prompts in Code
Aug 13, 2026Victoria Basmov, Yoav Goldberg, Reut TsarfatyPrompt Engineering Frozen Language Model
Bar-Ilan University · Allen Institute for Artificial Intelligence
Workflow Cards: Structured Summaries of Workflow Executions Using Provenance Data
Aug 11, 2026Nicola Giuseppe Marchioro, Gabriele Padovani, Amal Gueroudji +5Agentic Workflow Design Generation Provenance
University of Trento, Trento, Italy · Argonne National Laboratory, Lemont, IL, USA · Oak Ridge National Laboratory, Oak Ridge, TN, USA
Schema-Guided Hierarchical Information Extraction and Semantic Evaluation Using Generative AI
Aug 6, 2026Modhurita Mitra, Jan-Willem Versteeg, Maarten D. Schermer +3Information Extraction Schema
Research Engineering Team, Information and Technology Services, Utrecht University, Utrecht, The Netherlands · Division of Pharmacoepidemiology and Clinical Pharmacology, Utrecht Institute for Pharmaceutical Sciences, Utrecht University, Utrecht, The Netherlands
Consensus Measures for Unstructured Biomedical Text Annotations
Aug 4, 2026Pascal Wullschleger, Christian Kreis, Martin A. Walter +2Inter-Annotator Agreement Medical Ontology
Hamilton Institute, Maynooth University, Ireland · University of Lucerne, Switzerland · Lucerne School of Computer Science and IT, Switzerland
An Ontology-Guided, Deduplication-Aware Extraction Layer for Knowledge Graph Construction from Heterogeneous Documents
Jul 22, 2026Vaibhav Dangaich, Kevin Lewis, Kundeshwar PundalikKnowledge Graphs Relation Extraction
Benchmarking Generalization in Financial Statement Fraud Detection: robust evaluation and novel tasks
Jul 21, 2026Guy Stephane Waffo Dzuyo, Gaël Guibon, Christophe Cerisara +1Fraud Detection Financial Question Answering
Forvis Mazars · LORIA CNRS Université de Lorraine · LORIA, CNRS, Universit´e de Lorraine +2
DECODEM: Data Extraction from Corporate Organizational Documents via Enhanced Methods
Jul 17, 2026Jens FrankenreiterUnstructured Data Empirical Study
Washington University in St. Louis School of Law
DKCD: Domain Knowledge-Enhanced Causal Discovery from Unstructured Data
Jul 10, 2026Xin Li, Jin Li, Shoujin Wang +2Causal Discovery Methods Causal Graph
University of Technology Sydney · Sydney, NSW, Australia
Secret Scanner Agent: Extracting Secrets and Access Context from Unstructured Documents
Jul 10, 2026Zixiao Chen, Mariko Wakabayashi, Charlotte SiskaSecurity Evaluation Data Leakage
Microsoft, Redmond, WA, USA
SemJoin: Semantic Join Optimization
Jun 28, 2026Christopher Gou, Aditya Banerjee, Jiaxuan Wang +1Data Lakes Semantic Relationships
Purdue University
Source-Grounded Data Generation for Text-to-JSON Learning
Jun 18, 2026Sunghee Ahn, Guijin Son, Youngjae YuUnstructured Data Keyed Javascript Object Notation Record Yields
1Seoul National University
Evaluating Open-Source LLMs for Multi-Label ATT&CK Technique Classification on CTI Reports
Jun 16, 2026Ahmed Ryan, Saad Sakib Noor, Md Erfan +3Cyber Threat Intelligence Attacker Large Language Model
The University of Alabama · The University of Dhaka
Larch: Learned Query Optimization for Semantic Predicates
Jun 6, 2026Fuheng Zhao, Pawel Liskowski, Zihan Li +5Text-To-Sql Symbolic Predicates
Snowflake Inc. USA · Snowflake Inc. Poland
Wind Turbine Maintenance Log Labelling Framework: LLM-Driven Data Correction and Enrichment via Semantic Extraction of Reliability Intelligence
May 29, 2026Max Malyi, Jonathan Shek, Alasdair McDonald +1Offshore Wind Turbine Predictive Maintenance
Institute for Energy Systems, School of Engineering, The University of Edinburgh, Edinburgh, UK · 2Nadara, Lisbon, Portugal
Do Agents Need Semantic Metadata? A Comparative Study in Agentic Data Retrieval
May 27, 2026Shiyu Chen, Tarfah Alrashed, Alon Halevy +1Data Science Agents Metadata
Google, Mountain View, CA, USA
A Query Engine for the Agents
May 27, 2026Kenny DanielPersonalized Large Language Model Agents Unstructured Data
Hyperparam · Seattle, USA
Enhancing Regime Shift Detection Using Unstructured Data: A Study on the Treasury Market
May 17, 2026Mingxuan Yi, Vidal Mehra, Jing Chen +1Financial Sentiment Analysis Unstructured Data
School of Engineering Mathematics and Technology, University of Bristol, UK · Propellant Digital B.V., Amsterdam, Netherlands · School of Mathematics, Cardiff University, UK
Automated Population-Level Audit Assurance via AI-Based Document Intelligence
May 5, 2026Santosh Vasudevan, Velu NatarajanModel Auditing Unstructured Data
Caterpillar Inc., Chicago, IL, USA · GoodRx, Chicago, IL, USA
Enhance the after-discharge mortality rate prediction via learning from the medical notes
May 5, 2026Zijiang YangIntensive Care Unit Mortality Prediction Electronic Health Records
University of Texas at Austin, Austin TX 78712, USA
SchemaRAG: Dynamic Large Schema Reduction for LLM-driven Structured Information Extraction
May 4, 2026Sin Yu Bonnie Ho, Arlie Coles, Erik Larsson +3Information Extraction Schema
Microsoft
Structure-Aware Chunking for Tabular Data in Retrieval-Augmented Generation
May 1, 2026Pooja Guttal, Varun Magotra, Vasudeva Mahavishnu +3Chunk Tabular Data
Altumatim · University of Maryland, Baltimore County
From Unstructured to Structured: LLM-Guided Attribute Graphs for Entity Search and Ranking
Apr 30, 2026Yilun Zhu, Nikhita Vedula, Shervin MalmasiText Embeddings Similarity and Metrics
Amazon.com, Inc. Seattle, USA
Multiple Additive Neural Networks for Structured and Unstructured Data
Apr 29, 2026Janis Mohr, Jörg FrochteConvolutional Neural Networks Neural Network
Interdisciplinary Institute for Applied Artificial Intelligence and Data Science Ruhr Bochum University of Applied Sciences 42579 Heiligenhaus, Germany
Towards Agentic Investigation of Security Alerts
Apr 28, 2026Even Eilertsen, Vasileios Mavroeidis, Gudmund GrovSecurity Evaluation Cybersecurity
University of Oslo · Norwegian Defence Research Establishment (FFI) · & University of Oslo
Towards Automated Ontology Generation from Unstructured Text: A Multi-Agent LLM Approach
Apr 25, 2026Abid Talukder, Maruf Ahmed Mridul, Oshani SeneviratneOntology Multi-Agent Large Language Model Systems
Rensselaer Polytechnic Institute, Troy, New York, United States
ReLeVAnT: Relevance Lexical Vectors for Accurate Legal Text Classification
Apr 24, 2026Ishaan Gakhar, Harsh NandwaniLarge Language Model Classification Unstructured Data
Perssonify · Levi & Korsinsky
Making Interpretable Discoveries from Unstructured Data: A High-Dimensional Multiple Hypothesis Testing Approach
Nov 3, 2025Jacob CarlsonModel Discovery Unstructured Data
Harvard University∗
AgenticData: An Agentic Data Analytics System for Heterogeneous Data
Aug 7, 2025Ji Sun, Guoliang Li, Peiyao Zhou +3Data Science Agents Production Agentic Systems
Department of Computer Science, Tsinghua University
Random Rule Forest (RRF): Interpretable and Manageable Ensembles of LLM-Generated Questions for Predicting Success from Unstructured Data
May 30, 2025Ben Griffin, Aaron Ontoyin Yin, Diego Vidaurre +4Random Forest High-Stakes Domains
University of Oxford, United Kingdom · Vela Research, San Francisco, United States · Aarhus University, Aarhus, Denmark +2
Business as Rulesual: A Benchmark and Framework for Business Rule Flow Modeling with LLMs
May 24, 2025Chen Yang, Ruping Xu, Ruizhe Li +2Unstructured Data
Zhejiang University of Technology, China1 · Zhejiang Key Laboratory of Visual Information Intelligent Processing, China 2 · University of Aberdeen, UK +1

Sep 29, 2026, cs.LGJ/K move · Enter open · S save

Identifying ODEs from Unstructured Data with Causal Representation Learning

Alessandro Trenta, Riccardo Massidda, Davide Bacciu, Sara Magliacane

Department of Computer Science University of Pisa · Saarland Informatics Campus Saarland University & University of Amsterdam

Ordinary Differential Equations Causal Representation Learning Improving Sparse Autoencoders Unstructured Data

Open paper AskPDF arXiv

We study the problem of recovering the governing ODE of a dynamical system from unstructured, high-dimensional observations such as images. Existing methods for ODE discovery typically assume direct measurements of the variables, or do not provide theoretical guarantees on the learned variables and equations. While Causal Representation Learning (CRL) methods provide guarantees on identifying variables from high-dimensional observations up to component-wise diffeomorphisms, we show that in general these variables cannot be used directly as input to equation discovery methods, which typically assume that the variables will lead to sparse equations. So we introduce SParse Equivalent Equation Discovery AutoEncoder (SPEED-AE), a framework that combines a pretrained CRL method with a component-wise autoencoder that learns transformations of variables that are amenable to sparse ODE discovery. We show that for polynomial ODEs, this additional step allows us to restrict the identifiability of each variable from polynomial to monomial diffeomorphisms. Experiments on Lotka-Volterra, Lorenz, and a two-pendulum system show that SPEED-AE improves on the disentanglement of the CRL methods and that it recovers ODEs that are closest to the ground truth, while achieving state-of-the-art forecasting performance.

Momentum

Related topics

Latest papers 42