126 citations · 613 across the 33 of their papers we have counts for
35 papers
MONETA: Multimodal Industry Classification through Geographic Information with Multi Agent Systems
Arda Yüksel, Gabriel Thiem, Susanne Walter +3
Industry classification schemes are integral parts of public and corporate databases as they classify businesses based on economic activity. Due to the size of the company register…
The Conundrum of Trustworthy Research on Attacking Personally Identifiable Information Removal Techniques
Sebastian Ochs, Ivan Habernal
Removing personally identifiable information (PII) from texts is necessary to comply with various data protection regulations and to enable data sharing without compromising privac…
Legal Experts Disagree With Rationale Extraction Techniques for Explaining ECtHR Case Outcome Classification
Mahammad Namazov, Tomáš Koref, Ivan Habernal
Interpretability is critical for applications of large language models (LLMs) in the legal domain, where trust and transparency are essential. A central NLP task in this setting is…
Mining Legal Arguments to Study Judicial Formalism
Tomáš Koref, Lena Held, Mahammad Namazov +3
Courts must justify their decisions, but systematically analyzing judicial reasoning at scale remains difficult. This study tests claims about formalistic judging in Central and Ea…
Differentially-private text generation degrades output language quality
Erion Çano, Ivan Habernal
Ensuring user privacy by synthesizing data from large language models (LLMs) tuned under differential privacy (DP) has become popular recently. However, the impact of DP fine-tuned…
HiPS: Hierarchical PDF Segmentation of Doctrinal Legal Books
Sabine Wehnert, Harikrishnan Changaramkulath, Ivan Habernal
PDF parsers have recently improved on page-level layout understanding. However, recovering a document-global section hierarchy with reliable boundaries remains brittle for deeply s…
From ASR to ASP: Evaluating Prompt Attack Vulnerabilities Against Open-Source LLMs
Jiawen Wang, Pritha Gupta, Ivan Habernal +3
Recent studies demonstrate that Large Language Models (LLMs) are vulnerable to attacks that generate harmful or sensitive outputs. As open-source LLMs are increasingly adopted in h…
Transparent NLP: Using RAG and LLM Alignment for Privacy Q&A
Anna Leschanowsky, Zahra Kolagar, Erion Çano +4
The transparency principle of the General Data Protection Regulation (GDPR) requires data processing information to be clear, precise, and accessible. While language models show pr…
A Comprehensive Survey on Legal Summarization: Challenges and Future Directions
Mousumi Akter, Erion Çano, Erik Weber +2
This article provides a systematic up-to-date survey of automatic summarization techniques, datasets, models, and evaluation methods in the legal domain. Through specific source se…
Private Synthetic Text Generation with Diffusion Models
Sebastian Ochs, Ivan Habernal
How capable are diffusion models of generating synthetics texts? Recent research shows their strengths, with performance reaching that of auto-regressive LLMs. But are they also go…
Private Language Models via Truncated Laplacian Mechanism
Tianhao Huang, Tao Yang, Ivan Habernal +2
Deep learning models for NLP tasks are prone to variants of privacy attacks. To prevent privacy leakage, researchers have investigated word-level perturbations, relying on the form…
The Impact of Inference Acceleration on Bias of LLMs
Elisabeth Kirsten, Ivan Habernal, Vedant Nanda +1
Last few years have seen unprecedented advances in capabilities of Large Language Models (LLMs). These advancements promise to benefit a vast array of application domains. However,…
Problem Solving Through Human-AI Preference-Based Cooperation
Subhabrata Dutta, Timo Kaufmann, Goran Glavaš +7
While there is a widespread belief that artificial general intelligence (AGI) -- or even superhuman AI -- is imminent, complex problems in expert domains are far from being solved.…
Granularity is crucial when applying differential privacy to text: An investigation for neural machine translation
Doan Nam Long Vu, Timour Igamberdiev, Ivan Habernal
Applying differential privacy (DP) by means of the DP-SGD algorithm to protect individual data points during training is becoming increasingly popular in NLP. However, the choice o…
LaCour!: Enabling Research on Argumentation in Hearings of the European Court of Human Rights
Lena Held, Ivan Habernal
Why does an argument end up in the final court decision? Was it deliberated or questioned during the oral hearings? Was there something in the hearings that triggered a particular…
DP-NMT: Scalable Differentially-Private Machine Translation
Timour Igamberdiev, Doan Nam Long Vu, Felix Künnecke +3
Neural machine translation (NMT) is a widely popular text generation task, yet there is a considerable research gap in the development of privacy-preserving NMT models, despite sig…
To share or not to share: What risks would laypeople accept to give sensitive data to differentially-private NLP systems?
Christopher Weiss, Frauke Kreuter, Ivan Habernal
Although the NLP community has adopted central differential privacy as a go-to framework for privacy-preserving model training or data sharing, the choice and interpretation of the…
Trade-Offs Between Fairness and Privacy in Language Modeling
Cleo Matzken, Steffen Eger, Ivan Habernal
Protecting privacy in contemporary NLP models is gaining in importance. So does the need to mitigate social biases of such models. But can we have both at the same time? Existing r…
Crowdsourcing on Sensitive Data with Privacy-Preserving Text Rewriting
Nina Mouhammad, Johannes Daxenberger, Benjamin Schiller +1
Most tasks in NLP require labeled data. Data labeling is often done on crowdsourcing platforms due to scalability reasons. However, publishing data on public platforms can only be…
DP-BART for Privatized Text Rewriting under Local Differential Privacy
Timour Igamberdiev, Ivan Habernal
Privatized text rewriting with local differential privacy (LDP) is a recent approach that enables sharing of sensitive textual documents while formally guaranteeing privacy protect…
Differentially Private Natural Language Models: Recent Advances and Future Directions
Lijie Hu, Ivan Habernal, Lei Shen +1
Recent developments in deep learning have led to great success in various natural language processing (NLP) tasks. However, these applications may involve data that contain sensiti…
Privacy-Preserving Models for Legal Natural Language Processing
Ying Yin, Ivan Habernal
Pre-training large transformer models with in-domain data improves domain adaptation and helps gain performance on the domain-specific downstream tasks. However, sharing models pre…
The Legal Argument Reasoning Task in Civil Procedure
Leonard Bongard, Lena Held, Ivan Habernal
We present a new NLP task and dataset from the domain of the U.S. civil procedure. Each instance of the dataset consists of a general introduction to the case, a particular questio…
How Much User Context Do We Need? Privacy by Design in Mental Health NLP Application
Ramit Sawhney, Atula Tejaswi Neerkaje, Ivan Habernal +1
Clinical NLP tasks such as mental health assessment from text, must take social constraints into account - the performance maximization must be constrained by the utmost importance…