527 citations · 1.9k across the 46 of their papers we have counts for
58 papers
LAR-ECHR: A New Legal Argument Reasoning Task and Dataset for Cases of the European Court of Human Rights
Odysseas S. Chlapanis, Dimitrios Galanis, Ion Androutsopoulos
We present Legal Argument Reasoning (LAR), a novel task designed to evaluate the legal reasoning capabilities of Large Language Models (LLMs). The task requires selecting the corre…
Archimedes-AUEB at SemEval-2024 Task 5: LLM explains Civil Procedure
Odysseas S. Chlapanis, Ion Androutsopoulos, Dimitrios Galanis
The SemEval task on Argument Reasoning in Civil Procedure is challenging in that it requires understanding legal concepts and inferring complex arguments. Currently, most Large Lan…
Should I try multiple optimizers when fine-tuning pre-trained Transformers for NLP tasks? Should I tune their hyperparameters?
Nefeli Gkouti, Prodromos Malakasiotis, Stavros Toumpis +1
NLP research has explored different neural model architectures and sizes, datasets, training objectives, and transfer learning techniques. However, the choice of optimizer during t…
Cache me if you Can: an Online Cost-aware Teacher-Student framework to Reduce the Calls to Large Language Models
Ilias Stogiannidis, Stavros Vassos, Prodromos Malakasiotis +1
Prompting Large Language Models (LLMs) performs impressively in zero- and few-shot settings. Hence, small and medium-sized enterprises (SMEs) that cannot afford the cost of creatin…
Processing Long Legal Documents with Pre-trained Transformers: Modding LegalBERT and Longformer
Dimitris Mamakas, Petros Tsotsi, Ion Androutsopoulos +1
Pre-trained Transformers currently dominate most NLP tasks. They impose, however, limits on the maximum input length (512 sub-words in BERT), which are too restrictive in the legal…
Realistic Zero-Shot Cross-Lingual Transfer in Legal Topic Classification
Stratos Xenouleas, Alexia Tsoukara, Giannis Panagiotakis +2
We consider zero-shot cross-lingual transfer in legal topic classification using the recent MultiEURLEX dataset. Since the original dataset contains parallel documents, which is un…