arXiv subjects

Florian Matthes

Publications and source records attributed to Florian Matthes.

At least 37 records · Page 2Linked to original sources

arXiv2025

CRSet: Private Non-Interactive Verifiable Credential Revocation

Like any digital certificate, Verifiable Credentials (VCs) require a way to revoke them in case of an error or key compromise. Existing solutions for VC revocation, most prominently Bitstring Status List, are not viable for many use cases because they may leak the issuer's activity, which in turn leaks internal business metrics. For instance, staff fluctuation through the revocation of employee IDs. We identify the protection of issuer activity as a key gap and propose a formal definition for a corresponding characteristic of a revocation mechanism. Then, we introduce CRSet, a non-interactive mechanism that trades some space efficiency to reach these privacy characteristics. For that, we provide a proof sketch. Issuers periodically encode revocation data and publish it via Ethereum blob-carrying transactions, ensuring secure and private availability. Relying Parties (RPs) can download it to perform revocation checks locally. Sticking to a non-interactive design also makes adoption easier because it requires no changes to wallet agents and exchange protocols. We also implement and empirically evaluate CRSet, finding its real-world behavior to match expectations. One Ethereum blob fits revocation data for about 170k VCs.

cs.CR↗

arXiv2025

Facts Fade Fast: Evaluating Memorization of Outdated Medical Knowledge in Large Language Models

The growing capabilities of Large Language Models (LLMs) show significant potential to enhance healthcare by assisting medical researchers and physicians. However, their reliance on static training data is a major risk when medical recommendations evolve with new research and developments. When LLMs memorize outdated medical knowledge, they can provide harmful advice or fail at clinical reasoning tasks. To investigate this problem, we introduce two novel question-answering (QA) datasets derived from systematic reviews: MedRevQA (16,501 QA pairs covering general biomedical knowledge) and MedChangeQA (a subset of 512 QA pairs where medical consensus has changed over time). Our evaluation of eight prominent LLMs on the datasets reveals consistent reliance on outdated knowledge across all models. We additionally analyze the influence of obsolete pre-training data and training strategies to explain this phenomenon and propose future directions for mitigation, laying the groundwork for developing more current and reliable medical AI systems.

cs.CL↗

arXiv2025

FActBench: A Benchmark for Fine-grained Automatic Evaluation of LLM-Generated Text in the Medical Domain

Large Language Models tend to struggle when dealing with specialized domains. While all aspects of evaluation hold importance, factuality is the most critical one. Similarly, reliable fact-checking tools and data sources are essential for hallucination mitigation. We address these issues by providing a comprehensive Fact-checking Benchmark FActBench covering four generation tasks and six state-of-the-art Large Language Models (LLMs) for the Medical domain. We use two state-of-the-art Fact-checking techniques: Chain-of-Thought (CoT) Prompting and Natural Language Inference (NLI). Our experiments show that the fact-checking scores acquired through the Unanimous Voting of both techniques correlate best with Domain Expert Evaluation.

cs.CL↗

arXiv2025

Can Smaller LLMs do better? Unlocking Cross-Domain Potential through Parameter-Efficient Fine-Tuning for Text Summarization

Large Language Models (LLMs), being generic task solvers, are versatile. However, despite the vast amount of data they are trained on, there are speculations about their adaptation capabilities to a new domain. Additionally, the simple fine-tuning of the model to incorporate knowledge of a new domain is computationally expensive and time-consuming. This becomes more challenging when the domain in question is also low-resource, and labeled data is unavailable. We leverage parameter-efficient fine-tuning techniques (PEFTs) on high-resource datasets to address these challenges to improve performance on unseen low-resource domains. Throughout our experiments, we evaluate whether intrinsic linguistic commonalities between datasets can be leveraged for efficient domain adaptation. We benchmark six PEFTs with \texttt{Llama-3-8B-Instruct} on 14 training datasets from the Scientific, Medical, Legal, and News domains for a Text Summarization task. Our experiments show that for low-resource domains, inference using Within-Domain Adapters can achieve better performance than Few-Shot as well as a much larger \texttt{Llama-3-70B-Instruct}. Lastly, in the absence of Within-Domain Adapters, we explore the concept of using Cross-Domain Adapters as well as the strategic combinations of adapters to leverage intrinsic language similarities across domains, facilitating better adaptability and performance in low-resource settings.

cs.CL↗

arXiv2025

MedSEBA: Synthesizing Evidence-Based Answers Grounded in Evolving Medical Literature

In the digital age, people often turn to the Internet in search of medical advice and recommendations. With the increasing volume of online content, it has become difficult to distinguish reliable sources from misleading information. Similarly, millions of medical studies are published every year, making it challenging for researchers to keep track of the latest scientific findings. These evolving studies can reach differing conclusions, which is not reflected in traditional search tools. To address these challenges, we introduce MedSEBA, an interactive AI-powered system for synthesizing evidence-based answers to medical questions. It utilizes the power of Large Language Models to generate coherent and expressive answers, but grounds them in trustworthy medical studies dynamically retrieved from the research database PubMed. The answers consist of key points and arguments, which can be traced back to respective studies. Notably, the platform also provides an overview of the extent to which the most relevant studies support or refute the given medical claim, and a visualization of how the research consensus evolved through time. Our user study revealed that medical experts and lay users find the system usable and helpful, and the provided answers trustworthy and informative. This makes the system well-suited for both everyday health questions and advanced research insights.

cs.CL↗

arXiv2025

Leveraging Semantic Triples for Private Document Generation with Local Differential Privacy Guarantees

Many works at the intersection of Differential Privacy (DP) in Natural Language Processing aim to protect privacy by transforming texts under DP guarantees. This can be performed in a variety of ways, from word perturbations to full document rewriting, and most often under local DP. Here, an input text must be made indistinguishable from any other potential text, within some bound governed by the privacy parameter $\varepsilon$. Such a guarantee is quite demanding, and recent works show that privatizing texts under local DP can only be done reasonably under very high $\varepsilon$ values. Addressing this challenge, we introduce DP-ST, which leverages semantic triples for neighborhood-aware private document generation under local DP guarantees. Through the evaluation of our method, we demonstrate the effectiveness of the divide-and-conquer paradigm, particularly when limiting the DP notion (and privacy guarantees) to that of a privatization neighborhood. When combined with LLM post-processing, our method allows for coherent text generation even at lower $\varepsilon$ values, while still balancing privacy and utility. These findings highlight the importance of coherence in achieving balanced privatization outputs at reasonable $\varepsilon$ levels.

cs.CL↗

arXiv2025

The Double-edged Sword of LLM-based Data Reconstruction: Understanding and Mitigating Contextual Vulnerability in Word-level Differential Privacy Text Sanitization

Differentially private text sanitization refers to the process of privatizing texts under the framework of Differential Privacy (DP), providing provable privacy guarantees while also empirically defending against adversaries seeking to harm privacy. Despite their simplicity, DP text sanitization methods operating at the word level exhibit a number of shortcomings, among them the tendency to leave contextual clues from the original texts due to randomization during sanitization $\unicode{x2013}$ this we refer to as $\textit{contextual vulnerability}$. Given the powerful contextual understanding and inference capabilities of Large Language Models (LLMs), we explore to what extent LLMs can be leveraged to exploit the contextual vulnerability of DP-sanitized texts. We expand on previous work not only in the use of advanced LLMs, but also in testing a broader range of sanitization mechanisms at various privacy levels. Our experiments uncover a double-edged sword effect of LLM-based data reconstruction attacks on privacy and utility: while LLMs can indeed infer original semantics and sometimes degrade empirical privacy protections, they can also be used for good, to improve the quality and privacy of DP-sanitized texts. Based on our findings, we propose recommendations for using LLM data reconstruction as a post-processing step, serving to increase privacy protection by thinking adversarially.

cs.CR↗

arXiv2025

LLM-as-a-Judge for Privacy Evaluation? Exploring the Alignment of Human and LLM Perceptions of Privacy in Textual Data

Despite advances in the field of privacy-preserving Natural Language Processing (NLP), a significant challenge remains the accurate evaluation of privacy. As a potential solution, using LLMs as a privacy evaluator presents a promising approach $\unicode{x2013}$ a strategy inspired by its success in other subfields of NLP. In particular, the so-called $\textit{LLM-as-a-Judge}$ paradigm has achieved impressive results on a variety of natural language evaluation tasks, demonstrating high agreement rates with human annotators. Recognizing that privacy is both subjective and difficult to define, we investigate whether LLM-as-a-Judge can also be leveraged to evaluate the privacy sensitivity of textual data. Furthermore, we measure how closely LLM evaluations align with human perceptions of privacy in text. Resulting from a study involving 10 datasets, 13 LLMs, and 677 human survey participants, we confirm that privacy is indeed a difficult concept to measure empirically, exhibited by generally low inter-human agreement rates. Nevertheless, we find that LLMs can accurately model a global human privacy perspective, and through an analysis of human and LLM reasoning patterns, we discuss the merits and limitations of LLM-as-a-Judge for privacy evaluation in textual data. Our findings pave the way for exploring the feasibility of LLMs as privacy evaluators, addressing a core challenge in solving pressing privacy issues with innovative technical solutions.

cs.CL↗

arXiv2025

When Explainability Meets Privacy: An Investigation at the Intersection of Post-hoc Explainability and Differential Privacy in the Context of Natural Language Processing

In the study of trustworthy Natural Language Processing (NLP), a number of important research fields have emerged, including that of explainability and privacy. While research interest in both explainable and privacy-preserving NLP has increased considerably in recent years, there remains a lack of investigation at the intersection of the two. This leaves a considerable gap in understanding of whether achieving both explainability and privacy is possible, or whether the two are at odds with each other. In this work, we conduct an empirical investigation into the privacy-explainability trade-off in the context of NLP, guided by the popular overarching methods of Differential Privacy (DP) and Post-hoc Explainability. Our findings include a view into the intricate relationship between privacy and explainability, which is formed by a number of factors, including the nature of the downstream task and choice of the text privatization and explainability method. In this, we highlight the potential for privacy and explainability to co-exist, and we summarize our findings in a collection of practical recommendations for future work at this important intersection.

cs.CL↗

arXiv2025

LLMs for Legal Subsumption in German Employment Contracts

Legal work, characterized by its text-heavy and resource-intensive nature, presents unique challenges and opportunities for NLP research. While data-driven approaches have advanced the field, their lack of interpretability and trustworthiness limits their applicability in dynamic legal environments. To address these issues, we collaborated with legal experts to extend an existing dataset and explored the use of Large Language Models (LLMs) and in-context learning to evaluate the legality of clauses in German employment contracts. Our work evaluates the ability of different LLMs to classify clauses as "valid," "unfair," or "void" under three legal context variants: no legal context, full-text sources of laws and court rulings, and distilled versions of these (referred to as examination guidelines). Results show that full-text sources moderately improve performance, while examination guidelines significantly enhance recall for void clauses and weighted F1-Score, reaching 80\%. Despite these advancements, LLMs' performance when using full-text sources remains substantially below that of human lawyers. We contribute an extended dataset, including examination guidelines, referenced legal sources, and corresponding annotations, alongside our code and all log files. Our findings highlight the potential of LLMs to assist lawyers in contract legality review while also underscoring the limitations of the methods presented.

cs.CL↗

arXiv2025

Correcting Hallucinations in News Summaries: Exploration of Self-Correcting LLM Methods with External Knowledge

While large language models (LLMs) have shown remarkable capabilities to generate coherent text, they suffer from the issue of hallucinations -- factually inaccurate statements. Among numerous approaches to tackle hallucinations, especially promising are the self-correcting methods. They leverage the multi-turn nature of LLMs to iteratively generate verification questions inquiring additional evidence, answer them with internal or external knowledge, and use that to refine the original response with the new corrections. These methods have been explored for encyclopedic generation, but less so for domains like news summarization. In this work, we investigate two state-of-the-art self-correcting systems by applying them to correct hallucinated summaries using evidence from three search engines. We analyze the results and provide insights into systems' performance, revealing interesting practical findings on the benefits of search engine snippets and few-shot prompts, as well as high alignment of G-Eval and human evaluation.

cs.CL↗

arXiv2025

Cross-Chain Arbitrage: The Next Frontier of MEV in Decentralized Finance

Decentralized finance (DeFi) markets spread across Layer-1 (L1) and Layer-2 (L2) blockchains rely on arbitrage to keep prices aligned. Today most price gaps are closed against centralized exchanges (CEXes), whose deep liquidity and fast execution make them the primary venue for price discovery. As trading volume migrates on-chain, cross-chain arbitrage between decentralized exchanges (DEXes) will become the canonical mechanism for price alignment. Yet, despite its importance to DeFi-and the on-chain transparency making real activity tractable in a way CEX-to-DEX arbitrage is not-existing research remains confined to conceptual overviews and hypothetical opportunity analyses. We study cross-chain arbitrage with a profit-cost model and a year-long measurement. The model shows that opportunity frequency, bridging time, and token depreciation determine whether inventory- or bridge-based execution is more profitable. Empirically, we analyze one year of transactions (September 2023 - August 2024) across nine blockchains and identify 242,535 executed arbitrages totaling 868.64 million USD volume. Activity clusters on Ethereum-centric L1-L2 pairs, grows 5.5x over the study period, and surges-higher volume, more trades, lower fees-after the Dencun upgrade (March 13, 2024). Most trades use pre-positioned inventory (66.96%) and settle in 9s, whereas bridge-based arbitrages take 242s, underscoring the latency cost of today's bridges. Market concentration is high: the five largest addresses execute more than half of all trades, and one alone captures almost 40% of daily volume post-Dencun. We conclude that cross-chain arbitrage fosters vertical integration, centralizing sequencing infrastructure and economic power and thereby exacerbating censorship, liveness, and finality risks; decentralizing block building and lowering entry barriers are critical to countering these threats.

cs.CR↗

arXiv2025

Knowing Before Saying: LLM Representations Encode Information About Chain-of-Thought Success Before Completion

We investigate whether the success of a zero-shot Chain-of-Thought (CoT) process can be predicted before completion. We discover that a probing classifier, based on LLM representations, performs well \emph{even before a single token is generated}, suggesting that crucial information about the reasoning process is already present in the initial steps representations. In contrast, a strong BERT-based baseline, which relies solely on the generated tokens, performs worse, likely because it depends on shallow linguistic cues rather than deeper reasoning dynamics. Surprisingly, using later reasoning steps does not always improve classification. When additional context is unhelpful, earlier representations resemble later ones more, suggesting LLMs encode key information early. This implies reasoning can often stop early without loss. To test this, we conduct early stopping experiments, showing that truncating CoT reasoning still improves performance over not using CoT at all, though a gap remains compared to full reasoning. However, approaches like supervised learning or reinforcement learning designed to shorten CoT chains could leverage our classifier's guidance to identify when early stopping is effective. Our findings provide insights that may support such methods, helping to optimize CoT's efficiency while preserving its benefits.

cs.CL↗

arXiv2025

JaccDiv: A Metric and Benchmark for Quantifying Diversity of Generated Marketing Text in the Music Industry

Online platforms are increasingly interested in using Data-to-Text technologies to generate content and help their users. Unfortunately, traditional generative methods often fall into repetitive patterns, resulting in monotonous galleries of texts after only a few iterations. In this paper, we investigate LLM-based data-to-text approaches to automatically generate marketing texts that are of sufficient quality and diverse enough for broad adoption. We leverage Language Models such as T5, GPT-3.5, GPT-4, and LLaMa2 in conjunction with fine-tuning, few-shot, and zero-shot approaches to set a baseline for diverse marketing texts. We also introduce a metric JaccDiv to evaluate the diversity of a set of texts. This research extends its relevance beyond the music industry, proving beneficial in various fields where repetitive automated content generation is prevalent.

cs.CL↗

arXiv2025

Spend Your Budget Wisely: Towards an Intelligent Distribution of the Privacy Budget in Differentially Private Text Rewriting

The task of $\textit{Differentially Private Text Rewriting}$ is a class of text privatization techniques in which (sensitive) input textual documents are $\textit{rewritten}$ under Differential Privacy (DP) guarantees. The motivation behind such methods is to hide both explicit and implicit identifiers that could be contained in text, while still retaining the semantic meaning of the original text, thus preserving utility. Recent years have seen an uptick in research output in this field, offering a diverse array of word-, sentence-, and document-level DP rewriting methods. Common to these methods is the selection of a privacy budget (i.e., the $\varepsilon$ parameter), which governs the degree to which a text is privatized. One major limitation of previous works, stemming directly from the unique structure of language itself, is the lack of consideration of $\textit{where}$ the privacy budget should be allocated, as not all aspects of language, and therefore text, are equally sensitive or personal. In this work, we are the first to address this shortcoming, asking the question of how a given privacy budget can be intelligently and sensibly distributed amongst a target document. We construct and evaluate a toolkit of linguistics- and NLP-based methods used to allocate a privacy budget to constituent tokens in a text document. In a series of privacy and utility experiments, we empirically demonstrate that given the same privacy budget, intelligent distribution leads to higher privacy levels and more positive trade-offs than a naive distribution of $\varepsilon$. Our work highlights the intricacies of text privatization with DP, and furthermore, it calls for further work on finding more efficient ways to maximize the privatization benefits offered by DP in text rewriting.

cs.CR↗

arXiv2025

Investigating User Perspectives on Differentially Private Text Privatization

Recent literature has seen a considerable uptick in $\textit{Differentially Private Natural Language Processing}$ (DP NLP). This includes DP text privatization, where potentially sensitive input texts are transformed under DP to achieve privatized output texts that ideally mask sensitive information $\textit{and}$ maintain original semantics. Despite continued work to address the open challenges in DP text privatization, there remains a scarcity of work addressing user perceptions of this technology, a crucial aspect which serves as the final barrier to practical adoption. In this work, we conduct a survey study with 721 laypersons around the globe, investigating how the factors of $\textit{scenario}$, $\textit{data sensitivity}$, $\textit{mechanism type}$, and $\textit{reason for data collection}$ impact user preferences for text privatization. We learn that while all these factors play a role in influencing privacy decisions, users are highly sensitive to the utility and coherence of the private output texts. Our findings highlight the socio-technical factors that must be considered in the study of DP NLP, opening the door to further user-based investigations going forward.

cs.CL↗

arXiv2025

On the Influence of Context Size and Model Choice in Retrieval-Augmented Generation Systems

Retrieval-augmented generation (RAG) has emerged as an approach to augment large language models (LLMs) by reducing their reliance on static knowledge and improving answer factuality. RAG retrieves relevant context snippets and generates an answer based on them. Despite its increasing industrial adoption, systematic exploration of RAG components is lacking, particularly regarding the ideal size of provided context, and the choice of base LLM and retrieval method. To help guide development of robust RAG systems, we evaluate various context sizes, BM25 and semantic search as retrievers, and eight base LLMs. Moving away from the usual RAG evaluation with short answers, we explore the more challenging long-form question answering in two domains, where a good answer has to utilize the entire context. Our findings indicate that final QA performance improves steadily with up to 15 snippets but stagnates or declines beyond that. Finally, we show that different general-purpose LLMs excel in the biomedical domain than the encyclopedic one, and that open-domain evidence retrieval in large corpora is challenging.

cs.CL↗

arXiv2025

Step-by-Step Fact Verification System for Medical Claims with Explainable Reasoning

Fact verification (FV) aims to assess the veracity of a claim based on relevant evidence. The traditional approach for automated FV includes a three-part pipeline relying on short evidence snippets and encoder-only inference models. More recent approaches leverage the multi-turn nature of LLMs to address FV as a step-by-step problem where questions inquiring additional context are generated and answered until there is enough information to make a decision. This iterative method makes the verification process rational and explainable. While these methods have been tested for encyclopedic claims, exploration on domain-specific and realistic claims is missing. In this work, we apply an iterative FV system on three medical fact-checking datasets and evaluate it with multiple settings, including different LLMs, external web search, and structured reasoning using logic predicates. We demonstrate improvements in the final performance over traditional approaches and the high potential of step-by-step FV systems for domain-specific claims.

cs.CL↗