Paper accepted at IJCAI!
The paper entitled ‘The Alignment Bottleneck in Decomposition-Based Claim Verification’ has been accepted to International Joint Conference on Artificial Intelligence (IJCAI)!
☕️Federico Ruggeri
(he/him)
Postdoctoral Research Fellow
Professional Summary
I am a Postdoctoral Research Fellow in the Department of Computer Science and Engineering
(DISI) at the University of Bologna and a member of the Language Technologies Lab.
I develop natural language processing systems that extract structured knowledge from text
and integrate unstructured knowledge into interpretable models, with applications in
argument mining and legal analytics.
Education
PhD Computer Science
2018
2022
University of Bologna
MS Computer Science
2015
2018
University of Bologna
BS Computer Science
2012
2015
University of Bologna
Interests
Large Language Models
NLP
Interpretability
Knowledge Integration
Knowledge Extraction
📚 Research Focus
I study how natural language processing systems can generate, distill, and use knowledge from unstructured text. My work focuses on interpretable methods for argument mining and legal analytics along two complementary directions:
- Unstructured Knowledge Integration (UKI): enabling models to use large collections of textual knowledge when addressing a task.
- Structured Knowledge Extraction from Text: distilling structured, human-interpretable knowledge from raw text.
Selected Publications
(2026).
Let Guidelines Guide You: A Prescriptive Guideline-Centered Data Annotation Methodology.
Transactions of the Association for Computational Linguistics (TACL).
(2025).
Assessing the Reasoning Capabilities of LLMs in the context of Evidence-based Claim Verification.
Findings of the Association for Computational Linguistics: ACL 2025.
(2025).
Interlocking-free Selective Rationalization Through Genetic-based Learning.
Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).
(2025).
Untangling Hate Speech Definitions: A Semantic Componential Analysis Across Cultures and Domains.
Findings of the Association for Computational Linguistics: NAACL 2025.
(2025).
Promoting the Responsible Development of Speech Datasets for Mental Health and Neurological Disorders Research.
J. Artif. Intell. Res..
Recent News
Paper accepted at ICAIL!
The paper entitled ‘Evaluating LLMs as a Judge for Legal CJEU Decision Summarization’ has been accepted to International Conference on Artificial Intelligence and Law (ICAIL)!
Paper accepted at TACL!
My first-authored paper entitled ‘Let Guidelines Guide You: A Prescriptive Guideline-Centered Data Annotation Methodology’ has been accepted to TACL!
EquAl: Equitable Algorithms, Promoting Fairness and Countering Algorithmic Discrimination Through Norms and Technologies - Final Conference
I was invited to give a talk about the academic reproducibility crisis.