Ilias Chalkidis

Research Interests

My general field of research is in Artificial Intelligence, especially Natural Language Processing:

• NLP for Politics (Political Bias / LLMs as Voting Assistants)
• Legal Text Analytics (Legal NLP / NLU)
• Explainability / Interpretability of NLP models (XAI)
• AI Trustworthiness (Fairness & Robustness of NLP models)
• Large-scale Multi-label Text Classification (LMTC)
• Document to Document Information Retrieval (Doc2Doc IR)

Publications

-2024

• Investigating LLMs as Voting Assistants via Contextual Augmentation: A Case Study on the European Parliament Elections 2024

  Ilias Chalkidis

  In the Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP 2024), Miami, FL, USA, November 12-16, 2024

  Arxiv pre-print🤗 Dataset

• Breaking the Manual Annotation Bottleneck: Creating a Comprehensive Legal Case Criticality Dataset through Semi-Automated Labeling

  Ronja Stern, Ken Kawamura, Matthias Stürmer, Ilias Chalkidis, Joel Niklaus

  ArXiv Pre-print, 2024

  Arxiv pre-print

• Hyperbolic Contrastive Learning for Document Representations - A Multi-View Approach with Paragraph-level Similarities

  Jaeeun Nam, Ilias Chalkidis and Mina Rezaei

  In the Proceedings of the European Conference for Artificial Intelligence (ECAI 2024), Santiago de Compostela, Spain, October 19-24, 2024

  Article

• Attention-Driven Dropout: A Simple Augmentation Method to Improve Self-supervised Contrastive Sentence Embeddings

  Fabian Stermann, Ilias Chalkidis, Amirhossein Vahidi, Bernd Bischl, Mina Rezaei

  In the Proceedings of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD 2024), Vilnius, Lithuania, September 9-13, 2024

  Article

• MultiLegalPile: A 689GB Multilingual Legal Corpus (Outstanding Paper Award - ACL 2024 🏆)

  Joel Niklaus, Veton Matoshi, Matthias Stürmer, Ilias Chalkidis and Daniel E. Ho

  In the Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024), Bangkok, Thailand, August 11–16, 2024

  Arxiv pre-print Article🤗 Dataset🤗 Models

• On the Interplay between Fairness and Explainability

  Stephanie Brandl, Emanuele Bugliarello and Ilias Chalkidis

  In the Proceedings of the Workshop on Trustworthy Natural Language Processing (TrustNLP 2024), Mexico City, Mexico, June 21, 2024

  Arxiv pre-print Article

• Llama meets EU: Investigating the European Political Spectrum through the Lens of LLMs

  Ilias Chalkidis* and Stephanie Brandl*

  In the Proceedings of the Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 2023), Mexico City, Mexico, June 16–21, 2024

  Arxiv pre-print Article🤗 Dataset🤗 Models Code

• One Law, Many Languages: Benchmarking Multilingual Legal Reasoning for Judicial Support

  Vishvaksenan Rasiah, Ronja Stern, Veton Matoshi, Matthias Stürmer, Ilias Chalkidis, Daniel E. Ho, Joel Niklaus

  In the Proceedings of the Data-centric Machine Learning Research (DMLR) Workshop, Vienna, Austria, May 11, 2023

  Arxiv pre-print

-2023

• Rather a Nurse than a Physician - Contrastive Explanations under Investigation

  Oliver Eberle*, Ilias Chalkidis*, Laura Cabello and Stephanie Brandl

  In the Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP 2023), Singapore, December 6–10, 2023

  Arxiv pre-print Article🤗 Dataset Code

• Regulation and NLP (RegNLP): Taming Large Language Models

  Catalina Goanta, Nikolaos Aletras, Ilias Chalkidis, Sofia Ranchordas and Gerasimos Spanakis

  In the Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP 2023), Singapore, December 6–10, 2023

  Arxiv pre-print Article

• LEXTREME: A Multi-Lingual and Multi-Task Benchmark for the Legal Domain

  Joel Niklaus*, Veton Matoshi*, Pooja Rani, Andrea Galassi, Matthias Stürmer, and Ilias Chalkidis

  In Findings of Empirical Methods in Natural Language Processing (EMNLP 2023), 2023

  Arxiv pre-print🤗 Dataset Code

• SCALE: Scaling up the Complexity for Advanced Language Model Evaluation

  Vishvaksenan Rasiah, Ronja Stern, Veton Matoshi, Matthias Stürmer, Ilias Chalkidis, Daniel E. Ho and Joel Niklaus

  In the Proceedings of the Workshop on Natural Legal Language Processing - co-located with EMNLP 2023, Singapore, December 6–10, 2023

  Arxiv pre-print Article🤗 Dataset

• Retrieval-augmented Multi-label Text Classification

  Ilias Chalkidis* and Yova Kementchedjhieva*

  ArXiv Pre-print, 2023

  Arxiv pre-print

• LeXFiles and LegalLAMA: Facilitating English Multinational Legal Language Model Development

  Ilias Chalkidis*, Nicolas Garneau*, Catalina Goanta, Daniel Katz and Anders Søgaard

  In the Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (ACL 2023), Toronto, Canada, 9-14 July, 2023

  Arxiv pre-print Article🤗 Dataset Code🤗 Models

• An Exploration of Encoder-Decoder Approaches to Multi-Label Classification for Legal and Biomedical Text

  Yova Kementchedjhieva* and Ilias Chalkidis*

  In Findings of the 61st Annual Meeting of the Association for Computational Linguistics (ACL 2023), 2023

  Arxiv pre-print Article Code

• Efficient Document Embeddings via Self-Contrastive Bregman Divergence Learning

  Daniel Saggau, Mina Rezaei, Bernd Bischl and Ilias Chalkidis

  In Findings of the 61st Annual Meeting of the Association for Computational Linguistics (ACL 2023), 2023

  Arxiv pre-print Code

• PokemonChat: Auditing ChatGPT for Pokémon Universe Knowledge

  Laura Cabello, Jiaang Li, Ilias Chalkidis

  ArXiv Pre-print, 2023

  ArXiv pre-print

• Textual Information and IPO Underpricing: A Machine Learning Approach

  Apostolos Katsafados, George Leledakis, Emmanouil Pyrgiotakis, Ion Androutsopoulos, Ilias Chalkidis and Manos Fergadiotis

  In the Journal of Financial Data Science, Spring 2023.

  Article

• ChatGPT may Pass the Bar Exam soon, but has a Long Way to Go for the LexGLUE benchmark

  Ilias Chalkidis

  SSRN Pre-print, 2023

  SSRN pre-print Code

-2022

• Processing Long Legal Documents with Pre-trained Transformers: Modding LegalBERT and Longformer

  Dimitris Mamakas*, Petros Tsotsi*, Ion Androutsopoulos, and Ilias Chalkidis

  In the Proceedings of the Workshop on Natural Legal Language Processing - co-located with EMNLP 2022, Abu Dhabi, UAE, December 7–11, 2022

  Article Arxiv pre-print

• Legal-Tech Open Diaries: Lesson learned on how to develop and deploy light-weight models in the era of humongous Language Models

  Stelios Maroudas*, Sotiris Legkas*, Prodromos Malakasiotis, and Ilias Chalkidis

  In the Proceedings of the Workshop on Natural Legal Language Processing - co-located with EMNLP 2022, Abu Dhabi, UAE, December 7–11, 2022

  Article Arxiv pre-print

• An Exploration of Hierarchical Attention Transformers for Efficient Long Document Classification

  Ilias Chalkidis, Xiang Dai, Manos Fergadiotis, Prodromos Malakasiotis, and Desmond Elliott

  ArXiv Pre-print, 2022

  Arxiv pre-print Code🤗 Models

• Revisiting Transformer-based Models for Long Document Classification

  Xiang Dai, Ilias Chalkidis, Sune Darkner, and Desmond Elliott

  In Findings of the Conference on Empirical Methods in Natural Language Processing (EMNLP 2022), 2022

  Article Arxiv pre-print

• An Empirical Study on Cross-X Transfer for Legal Judgment Prediction

  Joel Niklaus*, Matthias Stürmer, and Ilias Chalkidis*

  In the Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (AACL-IJCNLP 2022), (Held online due to COVID-19), November 20-23, 2022

  Article Arxiv pre-print🤗 Dataset Code

• Realistic Zero-Shot Cross-Lingual Transfer in Legal Topic Classification

  Stratos Xenouleas, Alexia Tsoukara, Giannis Panagiotakis, Ilias Chalkidis, and Ion Androutsopoulos

  In the Proceedings of the 12th Hellenic Conference on Artificial Intelligence (SETN 2022), Corfu. Greece, September 7-9, 2022

  Article Arxiv pre-print🤗 Dataset Code

• Improved Multi-label Classification under Temporal Concept Drift: Rethinking Group-Robust Algorithms in a Label-Wise Setting

  Ilias Chalkidis and Anders Søgaard

  In Findings of the 60th Annual Meeting of the Association for Computational Linguistics (ACL 2022), 2022

  Article Arxiv pre-print Code

• FiNER: Financial Numeric Entity Recognition for XBRL Tagging

  Lefteris Loukas, Manos Fergadiotis, Prodromos Malakasiotis, Ilias Chalkidis, Eirini Spyropoulou, Ion Androutsopoulos, and Georgios Paliouras

  In the Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (ACL 2022), Dublin, Ireland, 23-25 May, 2022

  Article Arxiv pre-print🤗 Dataset Code🤗 Models

• FairLex: A Multilingual Benchmark for Evaluating Fairness in Legal Text Processing

  Ilias Chalkidis, Tommaso Pasini, Sheng Zhang, Letizia Tomada, Letizia, Sebastian Felix Schwemer, and Anders Søgaard

  In the Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (ACL 2022), Dublin, Ireland, 23-25 May, 2022

  Article Arxiv pre-print🤗 Dataset Code🤗 Models

• Challenges and Strategies in Cross-Cultural NLP

  Daniel Hershcovich, Stella Frank, Heather Lent, Miryam de Lhoneux, Mostafa Abdou, Stephanie Brandl, Emanuele Bugliarello, Laura Cabello Piqueras, Ilias Chalkidis, Ruixiang Cui, Constanza Fierro, Katerina Margatina, Phillip Rust, and Anders Søgaard

  In the Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (ACL 2022), Dublin, Ireland, 23-25 May, 2022

  Article Arxiv pre-print

• LexGLUE: A Benchmark Dataset for Legal Language Understanding in English

  Ilias Chalkidis, Abhik Jana, Dirk Hartung, Michael Bommarito, Ion Androutsopoulos, Daniel Martin Katz, and Nikolaos Aletras

  In the Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (ACL 2022), Dublin, Ireland, 23-25 May, 2022

  Article Arxiv pre-print🤗 Dataset Code

-2021

• Swiss-Judgment-Prediction: A Multilingual Legal Judgment Prediction Benchmark

  Joel Niklaus, Ilias Chalkidis, and Matthias Stürmer

  In the Proceedings of the Workshop on Natural Legal Language Processing - co-located with EMNLP 2021, Punta Cana, Dominican Republic, November 7–11, 2021

  Article Arxiv pre-print🤗 Dataset Code

• Multi-granular Legal Topic Classification on Greek Legislation

  Christos Papaloukas, Ilias Chalkidis, Konstantinos Athinaios, Despina-Athanasia Pantazi, and Manolis Koubarakis

  In the Proceedings of the Workshop on Natural Legal Language Processing - co-located with EMNLP 2021, Punta Cana, Dominican Republic, November 7–11, 2021.

  Article Arxiv pre-print🤗 Dataset Code

• MultiEURLEX - A multi-lingual and multi-label legal document classification dataset for zero-shot cross-lingual transfer

  Ilias Chalkidis, Manos Fergadiotis, and Ion Androutsopoulos

  In the Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP 2021), Punta Cana, Dominican Republic, November 7–11, 2021.

  Article Arxiv pre-print🤗 Dataset Code

• Deep Neural Networks for Information Mining from Legal Texts

  Ilias Chalkidis

  PhD Thesis, Department of Informatics, Athens University of Economics and Business, 2021

  Thesis

• Paragraph-level Rationale Extraction through Regularization: A case study on European Court of Human Rights Cases

  Ilias Chalkidis, Manos Fergadiotis, Dimitrios Tsarapatsanis, Nikolaos Aletras, Ion Androutsopoulos and Prodromos Malakasiotis

  In the Proceedings of the Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 2021), (Held online due to COVID-19), June 6–11, 2021

  Article Arxiv pre-print🤗 Dataset Presentation

• Neural Contract Element Extraction Revisited: Letters from Sesame Street

  Ilias Chalkidis, Manos Fergadiotis, Prodromos Malakasiotis and Ion Androutsopoulos

  Pre-print (Update of the article "Neural Contract Element Extraction Revisited"), February 23, 2021

  Arxiv pre-print

• Regulatory Compliance through Doc2Doc Information Retrieval: A case study in EU/UK legislation where text similarity has limitations

  Ilias Chalkidis, Manos Fergadiotis, Nikolaos Manginas and Prodromos Malakasiotis

  In the Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2021), (Held online due to COVID-19), April 21–23, 2021

  Article Arxiv pre-print Dataset

• Using Textual Analysis to Identify Merger Participants: Evidence from the U.S. Banking Industry

  Apostolos Katsafados, Ion Androutsopoulos, Ilias Chalkidis, Manos Fergadiotis, George Leledakis and Emmanouil Pyrgiotakis

  In Finance Research Letters, January 26, 2021.

  Article SSRN pre-print

-2020

• Layer-wise Guided Training for BERT: Learning Incrementally Refined Document Representations

  Nikolaos Manginas, Ilias Chalkidis and Prodromos Malakasiotis

  In the Proceedings of the Workshop on Structured Prediction for NLP (SPNLP 2020) - co-located with EMNLP 2020, (Held online due to COVID-19), November 16–20, 2020

  Article Arxiv pre-print

• An Empirical Study on Large-Scale Multi-Label Text Classification including Few and Zero-Shot Labels

  Ilias Chalkidis, Manos Fergadiotis, Sotiris Kotitsas, Prodromos Malakasiotis, Nikolaos Aletras and Ion Androutsopoulos

  In the Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP 2020), (Held online due to COVID-19), November 16–20, 2020.

  Article Arxiv pre-print Code

• LEGAL-BERT: "The Muppets straight out of Law School"

  Ilias Chalkidis, Manos Fergadiotis, Prodromos Malakasiotis, Nikolaos Aletras and Ion Androutsopoulos

  In Findings of Empirical Methods in Natural Language Processing (EMNLP 2020),(Held online due to COVID-19), November 16–20, 2020.

  Article Arxiv pre-print 🤗 Models

• Greek-BERT: The Greeks Visiting Sesame Street

  John Koutsikakis, Ilias Chalkidis, Prodromos Malakasiotis and Ion Androutsopoulos

  In the Proceedings of the 11th Hellenic Conference on Artificial Intelligence (SETN 2020), Athens, Greece, September 2-4, 2020.

  Article Arxiv pre-print 🤗 Models

-2019

• Neural Contract Element Extraction Revisited

  Ilias Chalkidis, Manos Fergadiotis, Prodromos Malakasiotis and Ion Androutsopoulos

  In the Proceedings of the Document Intelligence Workshop - co-located with NeurIPS 2019, Vancouver, Canada, December 8-14, 2019.

  Article Arxiv pre-print Poster

• Large-Scale Multi-Label Text Classification on EU Legislation

  Ilias Chalkidis, Manos Fergadiotis, Prodromos Malakasiotis and Ion Androutsopoulos

  In the Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (ACL 2019) (Short Papers), Florence, Italy, July 28 - August 2, 2019.

  Article Arxiv pre-print Poster Code Dataset

• Neural Legal Judgment Prediction in English

  Ilias Chalkidis, Ion Androutsopoulos and Nikolaos Aletras

  In the Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (ACL 2019) (Short Papers), Florence, Italy, July 28 - August 2, 2019.

  Article Arxiv pre-print Dataset

• Extreme Multi-Label Legal Text Classification: A case study in EU Legislation

  Ilias Chalkidis, Manos Fergadiotis, Prodromos Malakasiotis, Nikolaos Aletras and Ion Androutsopoulos

  In the Proceedings of the Workshop on Natural Legal Language Processing - co-located with NAACL-HLT 2019, Minneapolis, USA, June 2-7, 2019.

  Article Arxiv pre-print

• Towards a Decentralized, Trusted, Intelligent and Linked Public Sector: A Report from the Greek Trenches

  Themis Beris, Iosif Angelidis, Ilias Chalkidis, Charalampos Nikolau, Christos Papaloukas, Panagiotis Soursos and Manolis Koubarakis

  In the Proceedings of the Workshop on Linked Data on the Web and its Relationship with Distributed Ledgers (LDOW/LDDL) of the Web Conference 2019, San Francisco, USA, May 13-17, 2019.

  Article Arxiv pre-print

-2018

• Named Entity Recognition, Linking and Generation for Greek Legislation

  Iosif Angelidis, Ilias Chalkidis and Manolis Koubarakis

  In the Proceedings of the 31st International Conference on Legal Knowledge and Information Systems (JURIX 2018), Groningen, The Netherlands, December 12-14, 2018.

  Article Arxiv pre-print

• Deep Learning in Law: Early Adaptation and Legal Word Embeddings Trained on Large Corpora

  Ilias Chalkidis and Dimitrios Kampas

  In Artificial Intelligence and Law, Volume 27:2, Pages 171–198, Springer, December 11, 2018.

  Article Dataset

• Obligation and Prohibition Extraction Using Hierarchical RNNs

  Ilias Chalkidis‚ Ion Androutsopoulos and Achilleas Michos

  In the Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (ACL 2018) (Short Papers), Melbourne, Australia, July 15-20, 2018. Pages 254–259 . 2018.

  Article Arxiv pre-print Poster

• The Predictions of Bank Merger Targets and Acquirers with Textual Analysis

  George Leledakis, Apostolos Katsafados, Ion Androutsopoulos, Ilias Chalkidis, Emmanouel Fergadiotis

  In the Proceedings of the 9th National Conference of the Financial Engineering and Banking Society (FEBS 2018), Athens, Greece, 2018

-2017

• The Effect of Textual Information on IPO Underpricing

  Ion Androutsopoulos, Ilias Chalkidis, Emmanouel Fergadiotis, Apostolos Katsafados, George Leledakis and Alexandra Ntetsika

  In the Proceedings of the 8th National Conference of the Financial Engineering and Banking Society (FEBS 2017)‚ Athens‚ Greece‚ December 18-19‚ 2017. 2017.

• A Deep Learning Approach to Contract Element Extraction

  Ilias Chalkidis and Ion Androutsopoulos

  In the Proceedings of the 30th International Conference on Legal Knowledge and Information Systems (JURIX 2017)‚ Luxembourg City‚ Luxembourg‚ December 13-15‚ 2017. 2017.

  Article Arxiv pre-print

• Extracting Contract Elements

  Ilias Chalkidis‚ Ion Androutsopoulos and Achilleas Michos

  In Proceedings of the 16th International Conference on Artificial Intelligence and Law (ICAIL 2017), London, UK, June 12–16, 2017, Pages 19–28. 2017.

  Article Arxiv pre-print

• Modeling and Querying Greek Legislation using Semantic Web Technologies

  Ilias Chalkidis‚ Charalampos Nikolaou‚ Panagiotis Soursos and Manolis Koubarakis

  In the Proceedings of the 14th European Semantic Web Conference (ESWC 2017)‚ Portorož‚ Slovenia‚ May 28 − June 1‚ 2017. Pages 591–606. 2017.

  Article Arxiv pre-print