BZPEERReading, trust and collaboration for research
Menu

Discover

GraphFollow connections around a paper, topic or saved view.

Workspaces

HomePick up where your research flow left off.InboxHandle requests, replies and notifications from one place.CollectionsCurate reading lists, evidence sets and shareable dossiers.ResearchSee your private provenance graph, trail and imports.CollaborationMove from discovery into focused discussion rooms.PublishDraft, preview and publish full-text research articles.

Network

ExpertsFind specialists worth following or asking for help.CommunitiesJoin research circles organized around shared work.PartnersSee external organizations active around the same topics.

Opportunities

ListingsBrowse roles, calls and collaborations with clearer fit signals.

Account

Log inReturn to your reading and collaboration workspace.Create accountStart saving work, following people and joining teams.
Log inCreate account

Researcher profile

Florian Matthes

Florian Matthes contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate
Computation and LanguageCryptography and SecurityArtificial IntelligenceSoftware EngineeringComputational Engineering, Finance, and ScienceInformation RetrievalNetworking and Internet Architecture

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author
14works
0followers
7topics
4close collaborators

Actions

Decide how to stay connected

Follow researcher0

Identity and collaboration

How to connect with this researcher

Claiming links this public author record to a researcher profile and unlocks direct collaboration workflows.

Log in to claim

Direct collaboration

Open a focused conversation when the fit is right

Claim this author entity first to unlock direct invitations.

Research graph

See the researcher in context

Open full explorer

Inspect adjacent work, topics, institutions and collaborators without jumping out to a separate graph page.

Building this graph slice

BZPEER is loading the nearby papers, people, topics and institutions for this page.

Published work

14 published item(s)

preprint2026arXiv

A Systematic Exploration of Text Decomposition and Budget Distribution in Differentially Private Text Obfuscation

The goal of differentially private text obfuscation is to obfuscate, or "perturb", input texts with Differential Privacy (DP) guarantees, such that the private output texts are quantifiably indistinguishable from the originals. While perturbation at the word level is intuitive, meaningful text privatization happens on complete documents. Recent research has laid the groundwork for reasoning about privacy budget distribution, namely, how an overall $\varepsilon$ budget can be sensibly distributed among the component pieces of a text. We perform a systematic evaluation of multiple text decomposition and budget distribution techniques in the context of DP text obfuscation, testing how different methods for chunking texts can be combined with techniques for allocating $\varepsilon$ to these chunks. Our experiments reveal that such design choices are very important, as even with comparable privacy budgets, significantly different results can occur based on which methods are chosen. In this, we provide credible evidence of the feasibility of maximizing empirical trade-offs by optimizing DP obfuscation procedures.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Atomic Fact-Checking Increases Clinician Trust in Large Language Model Recommendations for Oncology Decision Support: A Randomized Controlled Trial

Question: Does atomic fact-checking, which decomposes AI treatment recommendations into individually verifiable claims linked to source guideline documents, increase clinician trust compared to traditional explainability approaches? Findings: In this randomized trial of 356 clinicians generating 7,476 trust ratings, atomic fact-checking produced a large effect on trust (Cohen's d = 0.94), increasing the proportion of clinicians expressing trust from 26.9% to 66.5%. Traditional transparency mechanisms showed a dose-response gradient of improvement over baseline (d = 0.25 to 0.50). Meaning: Decomposing AI recommendations into individually verifiable claims linked to source guidelines produces substantially higher clinician trust than traditional explainability approaches in high-stakes clinical decisions.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Semantic Non-Fungibility and Violations of the Law of One Price in Prediction Markets

Prediction markets are designed to aggregate dispersed information about future events, yet today's ecosystem is fragmented across heterogeneous operator-run platforms and blockchain-based protocols that independently list economically identical events. In the absence of a shared notion of event identity, liquidity fails to pool across venues, arbitrage becomes capital-intensive or unenforceable, and prices systematically violate the Law of One Price. As a result, market prices reflect platform-local beliefs rather than a single, globally aggregated probability, undermining the core information-aggregation function of prediction markets. We address this gap by introducing a semantic alignment framework that makes cross-platform event identity explicit through joint analysis of natural-language descriptions, resolution semantics, and temporal scope. Applying this framework, we construct the first human-validated, cross-platform dataset of aligned prediction markets, covering over 100 000 events across ten major venues from 2018 to 2025. Using this dataset, we show that roughly 6% of all events are concurrently listed across platforms and that semantically equivalent markets exhibit persistent execution-aware price deviations of 2-4% on average, even in highly liquid and information-rich settings. These mispricings give rise to persistent cross-platform arbitrage opportunities driven by structural frictions rather than informational disagreement. Overall, our results demonstrate that semantic non-fungibility is a fundamental barrier to price convergence, and that resolving event identity is a prerequisite for prediction markets to aggregate information at a global scale.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

SoK: Privacy Risks and Mitigations in Retrieval-Augmented Generation Systems

The continued promise of Large Language Models (LLMs), particularly in their natural language understanding and generation capabilities, has driven a rapidly increasing interest in identifying and developing LLM use cases. In an effort to complement the ingrained "knowledge" of LLMs, Retrieval-Augmented Generation (RAG) techniques have become widely popular. At its core, RAG involves the coupling of LLMs with domain-specific knowledge bases, whereby the generation of a response to a user question is augmented with contextual and up-to-date information. The proliferation of RAG has sparked concerns about data privacy, particularly with the inherent risks that arise when leveraging databases with potentially sensitive information. Numerous recent works have explored various aspects of privacy risks in RAG systems, from adversarial attacks to proposed mitigations. With the goal of surveying and unifying these works, we ask one simple question: What are the privacy risks in RAG, and how can they be measured and mitigated? To answer this question, we conduct a systematic literature review of RAG works addressing privacy, and we systematize our findings into a comprehensive set of privacy risks, mitigation techniques, and evaluation strategies. We supplement these findings with two primary artifacts: a Taxonomy of RAG Privacy Risks and a RAG Privacy Process Diagram. Our work contributes to the study of privacy in RAG not only by conducting the first systematization of risks and mitigations, but also by uncovering important considerations when mitigating privacy risks in RAG systems and assessing the current maturity of proposed mitigations.

0 citations0 reviewsNo code linkedOpen access
preprint2025arXiv

Improving Reliability and Explainability of Medical Question Answering through Atomic Fact Checking in Retrieval-Augmented LLMs

Large language models (LLMs) exhibit extensive medical knowledge but are prone to hallucinations and inaccurate citations, which pose a challenge to their clinical adoption and regulatory compliance. Current methods, such as Retrieval Augmented Generation, partially address these issues by grounding answers in source documents, but hallucinations and low fact-level explainability persist. In this work, we introduce a novel atomic fact-checking framework designed to enhance the reliability and explainability of LLMs used in medical long-form question answering. This method decomposes LLM-generated responses into discrete, verifiable units called atomic facts, each of which is independently verified against an authoritative knowledge base of medical guidelines. This approach enables targeted correction of errors and direct tracing to source literature, thereby improving the factual accuracy and explainability of medical Q&A. Extensive evaluation using multi-reader assessments by medical experts and an automated open Q&A benchmark demonstrated significant improvements in factual accuracy and explainability. Our framework achieved up to a 40% overall answer improvement and a 50% hallucination detection rate. The ability to trace each atomic fact back to the most relevant chunks from the database provides a granular, transparent explanation of the generated responses, addressing a major gap in current medical AI applications. This work represents a crucial step towards more trustworthy and reliable clinical applications of LLMs, addressing key prerequisites for clinical application and fostering greater confidence in AI-assisted healthcare.

0 citations0 reviewsNo code linkedOpen access
preprint2024arXiv

Evaluating Large Language Models in Semantic Parsing for Conversational Question Answering over Knowledge Graphs

Conversational question answering systems often rely on semantic parsing to enable interactive information retrieval, which involves the generation of structured database queries from a natural language input. For information-seeking conversations about facts stored within a knowledge graph, dialogue utterances are transformed into graph queries in a process that is called knowledge-based conversational question answering. This paper evaluates the performance of large language models that have not been explicitly pre-trained on this task. Through a series of experiments on an extensive benchmark dataset, we compare models of varying sizes with different prompting techniques and identify common issue types in the generated output. Our results demonstrate that large language models are capable of generating graph queries from dialogues, with significant improvements achievable through few-shot prompting and fine-tuning techniques, especially for smaller models that exhibit lower zero-shot performance.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Differential Privacy in Natural Language Processing: The Story So Far

As the tide of Big Data continues to influence the landscape of Natural Language Processing (NLP), the utilization of modern NLP methods has grounded itself in this data, in order to tackle a variety of text-based tasks. These methods without a doubt can include private or otherwise personally identifiable information. As such, the question of privacy in NLP has gained fervor in recent years, coinciding with the development of new Privacy-Enhancing Technologies (PETs). Among these PETs, Differential Privacy boasts several desirable qualities in the conversation surrounding data privacy. Naturally, the question becomes whether Differential Privacy is applicable in the largely unstructured realm of NLP. This topic has sparked novel research, which is unified in one basic goal: how can one adapt Differential Privacy to NLP methods? This paper aims to summarize the vulnerabilities addressed by Differential Privacy, the current thinking, and above all, the crucial next steps that must be considered.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Exploring privacy-enhancing technologies in the automotive value chain

Privacy-enhancing technologies (PETs) are becoming increasingly crucial for addressing customer needs, security, privacy (e.g., enhancing anonymity and confidentiality), and regulatory requirements. However, applying PETs in organizations requires a precise understanding of use cases, technologies, and limitations. This paper investigates several industrial use cases, their characteristics, and the potential applicability of PETs to these. We conduct expert interviews to identify and classify uses cases, a gray literature review of relevant open-source PET tools, and discuss how the use case characteristics can be addressed using PETs' capabilities. While we focus mainly on automotive use cases, the results also apply to other use case domains.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Exponential Randomized Response: Boosting Utility in Differentially Private Selection

A differentially private selection algorithm outputs from a finite set the item that approximately maximizes a data-dependent quality function. The most widely adopted mechanisms tackling this task are the pioneering exponential mechanism and permute-and-flip, which can offer utility improvements of up to a factor of two over the exponential mechanism. This work introduces a new differentially private mechanism for private selection and conducts theoretical and empirical comparisons with the above mechanisms. For reasonably common scenarios, our mechanism can provide utility improvements of factors significantly larger than two over the exponential and permute-and-flip mechanisms. Because the utility can deteriorate in niche scenarios, we recommend our mechanism to analysts who can tolerate lower utility for some datasets.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

PatternRank: Leveraging Pretrained Language Models and Part of Speech for Unsupervised Keyphrase Extraction

Keyphrase extraction is the process of automatically selecting a small set of most relevant phrases from a given text. Supervised keyphrase extraction approaches need large amounts of labeled training data and perform poorly outside the domain of the training data. In this paper, we present PatternRank, which leverages pretrained language models and part-of-speech for unsupervised keyphrase extraction from single documents. Our experiments show PatternRank achieves higher precision, recall and F1-scores than previous state-of-the-art approaches. In addition, we present the KeyphraseVectorizers package, which allows easy modification of part-of-speech patterns for candidate keyphrase selection, and hence adaptation of our approach to any domain.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Revealing the Landscape of Privacy-Enhancing Technologies in the Context of Data Markets for the IoT: A Systematic Literature Review

IoT data markets in public and private institutions have become increasingly relevant in recent years because of their potential to improve data availability and unlock new business models. However, exchanging data in markets bears considerable challenges related to disclosing sensitive information. Despite considerable research focused on different aspects of privacy-enhancing data markets for the IoT, none of the solutions proposed so far seems to find a practical adoption. Thus, this study aims to organize the state-of-the-art solutions, analyze and scope the technologies that have been suggested in this context, and structure the remaining challenges to determine areas where future research is required. To accomplish this goal, we conducted a systematic literature review on privacy enhancement in data markets for the IoT, covering 50 publications dated up to July 2020, and provided updates with 24 publications dated up to May 2022. Our results indicate that most research in this area has emerged only recently, and no IoT data market architecture has established itself as canonical. Existing solutions frequently lack the required combination of anonymization and secure computation technologies. Furthermore, there is no consensus on the appropriate use of blockchain technology for IoT data markets and a low degree of leveraging existing libraries or reusing generic data market architectures. We also identified significant challenges remaining, such as the copy problem and the recursive enforcement problem that-while solutions have been suggested to some extent-are often not sufficiently addressed in proposed designs. We conclude that privacy-enhancing technologies need further improvements to positively impact data markets so that, ultimately, the value of data is preserved through data scarcity and users' privacy and businesses-critical information are protected.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Revealing the State of the Art of Large-Scale Agile Development Research: A Systematic Mapping Study

Context: Success with agile methods in the small scale has led to an increasing adoption also in large development undertakings and organizations. Recent years have also seen an increasing amount of primary research on the topic, as well as a number of systematic literature reviews. However, there is no systematic overview of the whole research field. Objective: This work identifies, classifies, and evaluates the state of the art of research in large-scale agile development. Method: We conducted a systematic mapping study and rigorously selected 136 studies. We designed a classification framework and extracted key information from the studies. We synthesized the obtained data and created an overview of the state of the art. Results: This work contributes with (i) a description of large-scale agile endeavors reported in the industry, (ii) a systematic map of existing research in the field, (iii) an overview of influential studies, (iv) an overview of the central research themes, and (v) a research agenda for future research. Conclusion: This study portrays the state of the art in large-scale agile development and offers researchers and practitioners a reflection of the past thirteen years of research and practice on the large-scale application of agile methods.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Understanding the Implementation of Technical Measures in the Process of Data Privacy Compliance: A Qualitative Study

Modern privacy regulations, such as the General Data Protection Regulation (GDPR), address privacy in software systems in a technologically agnostic way by mentioning general "technical measures" for data privacy compliance rather than dictating how these should be implemented. An understanding of the concept of technical measures and how exactly these can be handled in practice, however, is not trivial due to its interdisciplinary nature and the necessary technical-legal interactions. We aim to investigate how the concept of technical measures for data privacy compliance is understood in practice as well as the technical-legal interaction intrinsic to the process of implementing those technical measures. We follow a research design that is 1) exploratory in nature, 2) qualitative, and 3) interview-based, with 16 selected privacy professionals in the technical and legal domains. Our results suggest that there is no clear mutual understanding and commonly accepted approach to handling technical measures. Both technical and legal roles are involved in the implementation of such measures. While they still often operate in separate spheres, a predominant opinion amongst the interviewees is to promote more interdisciplinary collaboration. Our empirical findings confirm the need for better interaction between legal and engineering teams when implementing technical measures for data privacy. We posit that interdisciplinary collaboration is paramount to a more complete understanding of technical measures, which currently lacks a mutually accepted notion. Yet, as strongly suggested by our results, there is still a lack of systematic approaches to such interaction. Therefore, the results strengthen our confidence in the need for further investigations into the technical-legal dynamic of data privacy compliance.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

AuthSC: Mind the Gap between Web and Smart Contracts

Although almost all information about Smart Contract addresses is shared via websites, emails, or other forms of digital communication, Blockchains and distributed ledger technology are unable to establish secure bindings between websites and corresponding Smart Contracts. For a user, it is impossible to differentiate whether a website links to a legitimate Smart Contract set up by owners of a business or to an illicit contract aiming to steal users' funds. Surprisingly, current attempts to solve this issue mostly comprise of information redundancy, e.g., displaying contract addresses multiple times in varying forms of images and texts. These processes are burdensome, as the user is responsible for verifying the correctness of an address. More importantly, they do not address the core issue, as the contract itself does not contain information about its authenticity. To solve current issues for these applications and increase security, we propose a solution that facilitates publicly issued SSL/TLS-certificates of Fully-Qualified Domain Names (FQDN) to ensure the authenticity of Smart Contracts and their owners. Our approach combines on-chain identity assertion utilizing signatures from the respective certificate and off-chain authentication of the Smart Contract stored on the Blockchain. This approach allows to tackle the aforementioned issue and further enables applications such as the identification of consortia members in permissioned networks. The system is open and transparent, as the only requirement for usage is ownership of an SSL/TLS-certificate. To enable privacy-preserving authenticated Smart Contracts, we allow one-way and two-way binding between website and contract. Further, low creation and maintenance costs, a widely accepted public key infrastructure and user empowerment will drive potential adaption of Ethereum Authenticated Smart Contracts (AuthSC).

0 citations0 reviewsNo code linkedOpen access