Data and Text Analytics Lab
DTALab is a research group at the University of Modena and Reggio Emilia developing trustworthy data-centric AI for heterogeneous data, language models and decision support.
Research focus
Evidence-grounded NLP & LLMs
Grounding language-model reasoning in explicit and verifiable evidence.
Data Integration & Explainable Analytics
Integrating heterogeneous data while making model decisions understandable.
Robust & Auditable AI
Building AI systems that remain reliable, fair and inspectable.
Data Intelligence & Decision Support
Transforming complex tabular and time-series data into actionable knowledge.
Latest Updates
-
FactFlip accepted at EMNLP 2026
Read more: FactFlip accepted at EMNLP 2026Our paper “The Trigger Is in the Embedding: Supervision-Free Discovery and Diagnosis of Universal Adversarial Triggers in Fact Verification” has been accepted as a Main…
-
Three Papers Accepted at CIKM 2026
Read more: Three Papers Accepted at CIKM 2026Three DTALab contributions have been accepted at CIKM 2026: two demo papers, TabgenQA and AEQUITAS, and one resource paper CFX-Bench.
-
DTALab at KDD 2026 in Jeju
Read more: DTALab at KDD 2026 in JejuDTALab is attending KDD 2026 in Jeju, represented by Sara Pederzoli with the work FinBench: A Benchmarking Framework for Stock Market Prediction and Portfolio Allocation.