arXiv subjects

Christin Katharina Kreutz

Publications and source records attributed to Christin Katharina Kreutz.

At least 19 recordsLinked to original sources

arXiv2026

Are Researchers Being Replaced by Artificial Intelligence?

A Nature survey from 2023 involving 1,600 researchers shows that scientists are ``concerned, as well as excited, by the increasing use of artificial-intelligence tools in research.'' This tension frames our central question: Are researchers being replaced by artificial intelligence? We argue that replacement is already underway-not as disappearance, but as a shift from researcher-as-creator to researcher-as-curator. As AI agents increasingly generate hypotheses, papers, and reviews, humans risk retaining responsibility while losing intellectual ownership. This article examines how AI is reshaping the scientific lifecycle and exposes the deeper danger: not that AI will fail to do science, but that humans may stop truly understanding it.

cs.CY↗

arXiv2026

Sim4IA-Bench: A User Simulation Benchmark Suite for Next Query and Utterance Prediction

Validating user simulation is a difficult task due to the lack of established measures and benchmarks, which makes it challenging to assess whether a simulator accurately reflects real user behavior. As part of the Sim4IA Micro-Shared Task at the Sim4IA Workshop, SIGIR 2025, we present Sim4IA-Bench, a simulation benchmark suit for the prediction of the next queries and utterances, the first of its kind in the IR community. Our dataset as part of the suite comprises 160 real-world search sessions from the CORE search engine. For 70 of these sessions, up to 62 simulator runs are available, divided into Task A and Task B, in which different approaches predicted users next search queries or utterances. Sim4IA-Bench provides a basis for evaluating and comparing user simulation approaches and for developing new measures of simulator validity. Although modest in size, the suite represents the first publicly available benchmark that links real search sessions with simulated next-query predictions. In addition to serving as a testbed for next query prediction, it also enables exploratory studies on query reformulation behavior, intent drift, and interaction-aware retrieval evaluation. We also introduce a new measure for evaluating next-query predictions in this task. By making the suite publicly available, we aim to promote reproducible research and stimulate further work on realistic and explainable user simulation for information access: https://github.com/irgroup/Sim4IA-Bench.

cs.IR↗

arXiv2025

First Workshop on Building Innovative Research Systems for Digital Libraries (BIRDS 2025)

We propose the first workshop on Building Innovative Research Systems for Digital Libraries (BIRDS) to take place at TPDL 2025 as a full-day workshop. BIRDS addresses practitioners working in digital libraries and GLAMs as well as researchers from computational domains such as data science, information retrieval, natural language processing, and data modelling. Our interdisciplinary workshop focuses on connecting members of both worlds. One of today's biggest challenges is the increasing information flood. Large language models like ChatGPT seem to offer good performance for answering questions on the web. So, shall we just build upon that idea and use chatbots in digital libraries? Or do we need to design and develop specialized and effective access paths? Answering these questions requires to connect different communities, practitioners from real digital libraries and researchers in the area of computer science. In brief, our workshop's goal is thus to support researchers and practitioners to build the next generation of innovative and effective digital library systems.

cs.DL↗

arXiv2025

Demonstrating Narrative Pattern Discovery from Biomedical Literature

Digital libraries maintain extensive collections of knowledge and need to provide effective access paths for their users. For instance, PubPharm, the specialized information service for Pharmacy in Germany, provides and develops access paths to their underlying biomedical document collection. In brief, PubPharm supports traditional keyword-based search, search for chemical structures, as well as novel graph-based discovery workflows, e.g., listing or searching for interactions between different pharmaceutical entities. This paper introduces a new search functionality, called narrative pattern mining, allowing users to explore context-relevant entities and entity interactions. We performed interviews with five domain experts to verify the usefulness of our prototype.

cs.IR↗

arXiv2025

THM@SimpleText 2025 -- Task 1.1: Revisiting Text Simplification based on Complex Terms for Non-Experts

Scientific text is complex as it contains technical terms by definition. Simplifying such text for non-domain experts enhances accessibility of innovation and information. Politicians could be enabled to understand new findings on topics on which they intend to pass a law, or family members of seriously ill patients could read about clinical trials. The SimpleText CLEF Lab focuses on exactly this problem of simplification of scientific text. Task 1.1 of the 2025 edition specifically handles the simplification of complex sentences, so very short texts with little context. To tackle this task we investigate the identification of complex terms in sentences which are rephrased using small Gemini and OpenAI large language models for non-expert readers.

cs.CL↗

arXiv2025

Data Discovery using LLMs -- A Study of Data User Behaviour

Data search for scientific research is more complex than a simple web search. The emergence of large language models (LLMs) and their applicability for scientific tasks offers new opportunities for researchers who are looking for data, e.g., to freely express their data needs instead of fitting them into restrictions of data catalogues and portals. However, this also creates uncertainty about whether LLMs are suitable for this task. To answer this question, we conducted a user study with 32 researchers. We qualitatively and quantitively analysed participants' information interaction behaviour while searching for data using LLMs in two data search tasks, one in which we prompted the LLM to behave as a persona. We found that participants interact with LLMs in natural language, but LLMs remain a tool for them rather than an equal conversational partner. This changes slightly when the LLM is prompted to behave as a persona, but the prompting only affects participants' user experience when they are already experienced in LLM use.

cs.DL↗

arXiv2025

Second SIGIR Workshop on Simulations for Information Access (Sim4IA 2025)

Simulations in information access (IA) have recently gained interest, as shown by various tutorials and workshops around that topic. Simulations can be key contributors to central IA research and evaluation questions, especially around interactive settings when real users are unavailable, or their participation is impossible due to ethical reasons. In addition, simulations in IA can help contribute to a better understanding of users, reduce complexity of evaluation experiments, and improve reproducibility. Building on recent developments in methods and toolkits, the second iteration of our Sim4IA workshop aims to again bring together researchers and practitioners to form an interactive and engaging forum for discussions on the future perspectives of the field. An additional aim is to plan an upcoming TREC/CLEF campaign.

cs.IR↗

arXiv2024

Investigating Bias in Political Search Query Suggestions by Relative Comparison with LLMs

Search query suggestions affect users' interactions with search engines, which then influences the information they encounter. Thus, bias in search query suggestions can lead to exposure to biased search results and can impact opinion formation. This is especially critical in the political domain. Detecting and quantifying bias in web search engines is difficult due to its topic dependency, complexity, and subjectivity. The lack of context and phrasality of query suggestions emphasizes this problem. In a multi-step approach, we combine the benefits of large language models, pairwise comparison, and Elo-based scoring to identify and quantify bias in English search query suggestions. We apply our approach to the U.S. political news domain and compare bias in Google and Bing.

cs.IR↗

arXiv2024

Report on the Workshop on Simulations for Information Access (Sim4IA 2024) at SIGIR 2024

This paper is a report of the Workshop on Simulations for Information Access (Sim4IA) workshop at SIGIR 2024. The workshop had two keynotes, a panel discussion, nine lightning talks, and two breakout sessions. Key takeaways were user simulation's importance in academia and industry, the possible bridging of online and offline evaluation, and the issues of organizing a companion shared task around user simulations for information access. We report on how we organized the workshop, provide a brief overview of what happened at the workshop, and summarize the main topics and findings of the workshop and future work.

cs.IR↗

arXiv2023

Aspect-Driven Structuring of Historical Dutch Newspaper Archives

Digital libraries oftentimes provide access to historical newspaper archives via keyword-based search. Historical figures and their roles are particularly interesting cognitive access points in historical research. Structuring and clustering news articles would allow more sophisticated access for users to explore such information. However, real-world limitations such as the lack of training data, licensing restrictions and non-English text with OCR errors make the composition of such a system difficult and cost-intensive in practice. In this work we tackle these issues with the showcase of the National Library of the Netherlands by introducing a role-based interface that structures news articles on historical persons. In-depth, component-wise evaluations and interviews with domain experts highlighted our prototype's effectiveness and appropriateness for a real-world digital library collection.

cs.DL↗

arXiv2023

Text Simplification of Scientific Texts for Non-Expert Readers

Reading levels are highly individual and can depend on a text's language, a person's cognitive abilities, or knowledge on a topic. Text simplification is the task of rephrasing a text to better cater to the abilities of a specific target reader group. Simplification of scientific abstracts helps non-experts to access the core information by bypassing formulations that require domain or expert knowledge. This is especially relevant for, e.g., cancer patients reading about novel treatment options. The SimpleText lab hosts the simplification of scientific abstracts for non-experts (Task 3) to advance this field. We contribute three runs employing out-of-the-box summarization models (two based on T5, one based on PEGASUS) and one run using ChatGPT with complex phrase identification.

cs.CL↗

arXiv2023

Enriching Simple Keyword Queries for Domain-Aware Narrative Retrieval

Providing effective access paths to content is a key task in digital libraries. Oftentimes, such access paths are realized through advanced query languages, which, on the one hand, users may find challenging to learn or use, and on the other, requires libraries to convert their content into a high quality structured representation. As a remedy, narrative information access proposes to query library content through structured patterns directly, to ensure validity and coherence of information. However, users still find it challenging to express their information needs in such patterns. Therefore, this work bridges the gap by introducing a method that deduces patterns from keyword searches. Moreover, our user studies with participants from the biomedical domain show their acceptance of our prototypical system.

cs.DL↗

arXiv2023

Bibliometric Data Fusion for Biomedical Information Retrieval

Digital libraries in the scientific domain provide users access to a wide range of information to satisfy their diverse information needs. Here, ranking results play a crucial role in users' satisfaction. Exploiting bibliometric metadata, e.g., publications' citation counts or bibliometric indicators in general, for automatically identifying the most relevant results can boost retrieval performance. This work proposes bibliometric data fusion, which enriches existing systems' results by incorporating bibliometric metadata such as citations or altmetrics. Our results on three biomedical retrieval benchmarks from TREC Precision Medicine (TREC-PM) show that bibliometric data fusion is a promising approach to improve retrieval performance in terms of normalized Discounted Cumulated Gain (nDCG) and Average Precision (AP), at the cost of the Precision at 10 (P@10) rate. Patient users especially profit from this lightweight, data-sparse technique that applies to any digital library.

cs.DL↗

arXiv2023

Evaluating Digital Library Search Systems by using Formal Process Modelling

Evaluations of digital library information systems are typically centred on users correctly, efficiently, and quickly performing predefined tasks. Additionally, users generally enjoy working with the evaluated system, and completed questionnaires show an interface's excellent user experience. However, such evaluations do not explicitly consider comparing or connecting user-specific information-seeking behaviour with digital library system capabilities and thus overlook actual user needs or further system requirements. We aim to close this gap by introducing the usage of formalisations of users' task conduction strategies to compare their information needs with the capabilities of such information systems. We observe users' strategies in scope of expert finding and paper search. We propose and investigate using the business process model notation to formalise task conduction strategies and the SchenQL digital library interface as an example system. We conduct interviews in a qualitative evaluation with 13 participants from various backgrounds from which we derive models. We discovered that the formalisations are suitable and helpful to mirror the strategies back to users and to compare users' ideal task conductions with capabilities of information systems. We conclude using formal models for qualitative digital library studies being a suitable mean to identify current limitations and depict users' task conduction strategies. Our published dataset containing the evaluation data can be reused to investigate other digital library systems' fit for depicting users' ideal task solutions.

cs.DL↗

arXiv2023

Capturing Stability of Information Needs in Digital Libraries

Scientific digital libraries provide users access to large amounts of data to satisfy their diverse information needs. Factors influencing users' decisions on the relevancy of a publication or a person are individual and usually only visible through posed queries or clicked information. However, the actual formulation or consideration of information requirements begins earlier in users' exploration processes. Hence, we propose capturing the (in)stability of factors supporting these relevancy decisions through users' different levels of manifestation.

cs.DL↗

arXiv2022

Scientific Paper Recommendation Systems: a Literature Review of recent Publications

Scientific writing builds upon already published papers. Manual identification of publications to read, cite or consider as related papers relies on a researcher's ability to identify fitting keywords or initial papers from which a literature search can be started. The rapidly increasing amount of papers has called for automatic measures to find the desired relevant publications, so-called paper recommendation systems. As the number of publications increases so does the amount of paper recommendation systems. Former literature reviews focused on discussing the general landscape of approaches throughout the years and highlight the main directions. We refrain from this perspective, instead we only consider a comparatively small time frame but analyse it fully. In this literature review we discuss used methods, datasets, evaluations and open challenges encountered in all works first released between January 2019 and October 2021. The goal of this survey is to provide a comprehensive and complete overview of current paper recommendation systems.

cs.DL↗

arXiv2022

SchenQL: A query language for bibliographic data with aggregations and domain-specific functions

Current search interfaces of digital libraries are not suitable to satisfy complex or convoluted information needs directly, when it comes to cases such as "Find authors who only recently started working on a topic". They might offer possibilities to obtain this information only by requiring vast user interaction. We present SchenQL, a web interface of a domain-specific query language on bibliographic metadata, which offers information search and exploration by query formulation and navigation in the system. Our system focuses on supporting aggregation of data and providing specialised domain dependent functions while being suitable for domain experts as well as casual users of digital libraries.

cs.DL↗

arXiv2022

Diverse Reviewer Suggestion for Extending Conference Program Committees

Automated reviewer recommendation for scientific conferences currently relies on the assumption that the program committee has the necessary expertise to handle all submissions. However, topical discrepancies between received submissions and reviewer candidates might lead to unreliable reviews or overburdening of reviewers, and may result in the rejection of high-quality papers. In this work, we present DiveRS, an explainable flow-based reviewer assignment approach, which automatically generates reviewer assignments as well as suggestions for extending the current program committee with new reviewer candidates. Our algorithm focuses on the diversity of the set of reviewers assigned to papers, which has been mostly disregarded in prior work. Specifically, we consider diversity in terms of professional background, location and seniority. Using two real world conference datasets for evaluation, we show that DiveRS improves diversity compared to both real assignments and a state-of-the-art flow-based reviewer assignment approach. Further, based on human assessments by former PC chairs, we find that DiveRS can effectively trade off some of the topical suitability in order to construct more diverse reviewer assignments.

cs.DL↗