48 citations · 121 across the 23 of their papers we have counts for
24 papers
Synthetic Pre-pretraining Survives Scale, but Not as a Grammatical Prior
Atsuki Yamaguchi, Tatsuro Inaba, Joel Niklaus +3
Pre-pretraining (PPT) on synthetic non-natural language data improves token efficiency during language model pre-training (PT). Prior work attributes this gain to a grammatical pri…
How Can We Synthesize High-Quality Pretraining Data? A Systematic Study of Prompt Design, Generator Model, and Source Data
Joel Niklaus, Atsuki Yamaguchi, Michal Štefánik +9
Synthetic data is a standard component in training large language models, yet systematic comparisons across design dimensions, including rephrasing strategy, generator model, and s…
Parity-Aware Byte-Pair Encoding: Improving Cross-lingual Fairness in Tokenization
Negar Foroutan, Clara Meister, Debjit Paul +4
Tokenization is the first -- and often least scrutinized -- step of most NLP pipelines. Standard algorithms for learning tokenizers rely on frequency-based objectives, which favor…
LEXam: Benchmarking Legal Reasoning on 340 Law Exams
Yu Fan, Jingwei Ni, Jakob Merane +14
Long-form legal reasoning remains a key challenge for large language models (LLMs) in spite of recent advances in test-time scaling. To address this, we introduce LEXam, a novel be…
SwiLTra-Bench: The Swiss Legal Translation Benchmark
Joel Niklaus, Jakob Merane, Luka Nenadic +16
In Switzerland legal translation is uniquely important due to the country's four official languages and requirements for multilingual legal documentation. However, this process tra…
INCLUDE: Evaluating Multilingual Language Understanding with Regional Knowledge
Angelika Romanou, Negar Foroutan, Anna Sotnikova +56
The performance differential of large language models (LLM) between languages hinders their effective deployment in many regions, inhibiting the potential economic and societal val…
From Citations to Criticality: Predicting Legal Decision Influence in the Multilingual Swiss Jurisprudence
Ronja Stern, Ken Kawamura, Matthias Stürmer +2
Many court systems are overwhelmed all over the world, leading to huge backlogs of pending cases. Effective triage systems, like those in emergency rooms, could ensure proper prior…
Unlocking Legal Knowledge: A Multilingual Dataset for Judicial Summarization in Switzerland
Luca Rolshoven, Vishvaksenan Rasiah, Srinanda Brügger Bose +4
Legal research depends on headnotes: concise summaries that help lawyers quickly identify relevant cases. Yet, many court decisions lack them due to the high cost of manual annotat…
LawInstruct: A Resource for Studying Language Model Adaptation to the Legal Domain
Joel Niklaus, Lucia Zheng, Arya D. McCarthy +7
Instruction tuning is an important step in making language models useful for direct user interaction. However, the legal domain is underrepresented in typical instruction datasets…
Towards Explainability and Fairness in Swiss Judgement Prediction: Benchmarking on a Multilingual Dataset
Santosh T. Y. S. S, Nina Baumgartner, Matthias Stürmer +2
The assessment of explainability in Legal Judgement Prediction (LJP) systems is of paramount importance in building trustworthy and transparent systems, particularly considering th…
LegalLens: Leveraging LLMs for Legal Violation Identification in Unstructured Text
Dor Bernsohn, Gil Semo, Yaron Vazana +5
In this study, we focus on two main tasks, the first for detecting legal violations within unstructured textual data, and the second for associating these violations with potential…
Automatic Anonymization of Swiss Federal Supreme Court Rulings
Joel Niklaus, Robin Mamié, Matthias Stürmer +2
Releasing court decisions to the public relies on proper anonymization to protect all involved parties, where necessary. The Swiss Federal Supreme Court relies on an existing syste…
Resolving Legalese: A Multilingual Exploration of Negation Scope Resolution in Legal Documents
Ramona Christen, Anastassia Shaitarova, Matthias Stürmer +1
Resolving the scope of a negation within a sentence is a challenging NLP task. The complexity of legal texts and the lack of annotated in-domain negation corpora pose challenges fo…
LegalBench: A Collaboratively Built Benchmark for Measuring Legal Reasoning in Large Language Models
Neel Guha, Julian Nyarko, Daniel E. Ho +37
The advent of large language models (LLMs) and their adoption by the legal community has given rise to the question: what types of legal reasoning can LLMs perform? To enable great…
Anonymity at Risk? Assessing Re-Identification Capabilities of Large Language Models
Alex Nyffenegger, Matthias Stürmer, Joel Niklaus
Anonymity of both natural and legal persons in court rulings is a critical aspect of privacy protection in the European Union and Switzerland. With the advent of LLMs, concerns abo…
One Law, Many Languages: Benchmarking Multilingual Legal Reasoning for Judicial Support
Ronja Stern, Vishvaksenan Rasiah, Veton Matoshi +5
Recent strides in Large Language Models (LLMs) have saturated many Natural Language Processing (NLP) benchmarks, emphasizing the need for more challenging ones to properly assess L…
MultiLegalPile: A 689GB Multilingual Legal Corpus
Joel Niklaus, Veton Matoshi, Matthias Stürmer +2
Large, high-quality datasets are crucial for training Large Language Models (LLMs). However, so far, there are few datasets available for specialized critical domains such as law a…
MultiLegalSBD: A Multilingual Legal Sentence Boundary Detection Dataset
Tobias Brugger, Matthias Stürmer, Joel Niklaus
Sentence Boundary Detection (SBD) is one of the foundational building blocks of Natural Language Processing (NLP), with incorrectly split sentences heavily influencing the output q…
LEXTREME: A Multi-Lingual and Multi-Task Benchmark for the Legal Domain
Joel Niklaus, Veton Matoshi, Pooja Rani +3
Lately, propelled by the phenomenal advances around the transformer architecture, the legal NLP field has enjoyed spectacular growth. To measure progress, well curated and challeng…
BudgetLongformer: Can we Cheaply Pretrain a SotA Legal Language Model From Scratch?
Joel Niklaus, Daniele Giofré
Pretrained transformer models have achieved state-of-the-art results in many tasks and benchmarks recently. Many state-of-the-art Language Models (LMs), however, do not scale well…
ClassActionPrediction: A Challenging Benchmark for Legal Judgment Prediction of Class Action Cases in the US
Gil Semo, Dor Bernsohn, Ben Hagag +2
The research field of Legal Natural Language Processing (NLP) has been very active recently, with Legal Judgment Prediction (LJP) becoming one of the most extensively studied tasks…
An Empirical Study on Cross-X Transfer for Legal Judgment Prediction
Joel Niklaus, Matthias Stürmer, Ilias Chalkidis
Cross-lingual transfer learning has proven useful in a variety of Natural Language Processing (NLP) tasks, but it is understudied in the context of legal NLP, and not at all in Leg…
Swiss-Judgment-Prediction: A Multilingual Legal Judgment Prediction Benchmark
Joel Niklaus, Ilias Chalkidis, Matthias Stürmer
In many jurisdictions, the excessive workload of courts leads to high delays. Suitable predictive AI models can assist legal professionals in their work, and thus enhance and speed…
Survey of Artificial Intelligence for Card Games and Its Application to the Swiss Game Jass
Joel Niklaus, Michele Alberti, Vinaychandran Pondenkandath +2
In the last decades we have witnessed the success of applications of Artificial Intelligence to playing games. In this work we address the challenging field of games with hidden in…