Web Engineering Seminar (SS 2026)

Research Questions

• Which parts of the research process can current AI systems already perform effectively (if any)?
• How are AI-driven research systems built and implemented?
• What technical limitations currently exist for autonomous AI-based research?
• How trustworthy are AI-driven research systems with regard to factual accuracy, hallucinations, and reliability across different stages of the research process?
• How should attribution and authorship be assigned when AI systems contribute to the research process or its outputs?

Literature

• Own research
• https://www.nature.com/articles/s41586-026-10265-5

Research Questions

• What are the different stages in research? Present them and explain the general workflow.
• Where can AI tools be used in this process? Where can they help? What are inherent risks in using AI tools?
• Search at least 7 different AI tools for each stage and compare them according to their functionalities (Do you find reviews/testimonials/scientific as a basis? If not, create an evaluation scheme by first making notes on all features and then use coding techniques to create themes which can be compared). All AI tools should be free, accessible, and specifically for this research step (this does NOT include general LLMs like ChatGPT!).
• Choose one tool for each research step and use it in your own research for this seminar topic. Critically assess the output of the tools, verify it and correct it where necessary.
• Present your evaluation, argue for your choice of tools and reflect on the process using this tool.
• Which platforms exist, which include more stages of the complete research process? Present at least 5 and compare them. Choose one and try it on your own research topic. How do the results differentiate from your previous results?

Literature

• Own research
• https://www.tu-chemnitz.de/ub/kurse-und-e-learning/elearning/studierende/mika/index.html.en
• https://libguides.umn.edu/StructureResearchPaper
• https://www.kth.se/en/larande/sprak/utbildning/sprak/eng/writing-guide/writing-conventions/the-imrad-format-for-research-and-lab-reports-1.1395046
• Pinzolits, R. (2023). AI in academia: An overview of selected tools and their areas of application. MAP Education and Humanities, 4, 37–50. https://doi.org/10.53880/2744-2373.2023.4.37
• Venkatesh, V. Adoption and use of AI tools: a research agenda grounded in UTAUT. Ann Oper Res 308, 641–652 (2022). https://doi.org/10.1007/s10479-020-03918-9
• Oyelude AA (2024), “Artificial intelligence (AI) tools for academic research”. Library Hi Tech News, Vol. 41 No. 8 pp. 18–20, doi: https://doi.org/10.1108/LHTN-08-2024-0131

Research Questions

• What guidelines and principles exist to safeguard Good Research Practice?
• How can these guidelines and principles be integrated into the research process?
• What is scientific misconduct/scientific malpractice?
• What is considered “high-quality research”? What are indicators thereof?
• How do major computer science publishers address attribution in the age of LLMs?

Literature

• Own research
• The European Code of Conduct for Research Integrity
• Guidelines for Safeguarding Good Research Practice
• https://erc.europa.eu/sites/default/files/document/file/ERC_info_document-Open_Research_Data_and_Data_Management_Plans.pdf

Research Questions

• What is the definition of prompt engineering, context engineering, and harness engineering in LLM systems?
• How should the relationship among prompt engineering, context engineering, and harness engineering be understood: as replacement, progression, or hierarchical nesting?
• What are their main strengths and weaknesses?
• How to visualize the changing process of human-LLM interaction?

Literature

• Own research
• Sahoo, P., Singh, A. K., Saha, S., Jain, V., Mondal, S., & Chadha, A. (2024). A systematic survey of prompt engineering in large language models: Techniques and applications. arXiv preprint arXiv:2402.07927, 1.
• Mei, L., Yao, J., Ge, Y., Wang, Y., Bi, B., Cai, Y., … & Liu, S. (2025). A survey of context engineering for large language models. arXiv preprint arXiv:2507.13334.
• Yao, S., Zhao, J., Yu, D., Du, N., Shafran, I., Narasimhan, K. R., & Cao, Y. (2022, October). React: Synergizing reasoning and acting in language models. In The eleventh international conference on learning representations.
• Yu, C., Cheng, Z., Cui, H., Gao, Y., Luo, Z., Wang, Y., … & Zhao, Y. (2025, May). A survey on agent workflow–status and future. In 2025 8th International Conference on Artificial Intelligence and Big Data (ICAIBD) (pp. 770-781). IEEE.

Research Questions

• How can LLMs enhance knowledge graphs？
• How can knowledge graphs enhance LLMs?
• What are the main forms of collaboration between LLMs and knowledge graphs in current research and practical applications?
• Develop a visualization demo for GraphRAG..

Literature

• Own research
• Bian, H. (2025). LLM-empowered knowledge graph construction: A survey. arXiv preprint arXiv:2510.20345.
• Edge, D., Trinh, H., Cheng, N., Bradley, J., Chao, A., Mody, A., … & Larson, J. (2024). From local to global: A graph rag approach to query-focused summarization. arXiv preprint arXiv:2404.16130.
• Wu, J., Zhu, J., Qi, Y., Chen, J., Xu, M., Menolascina, F., & Grau, V. (2024). Medical graph rag: Towards safe medical large language model via graph retrieval-augmented generation. arXiv preprint arXiv:2408.04187.
• Ma, C., Chen, Y., Wu, T., Khan, A., & Wang, H. (2025, November). Large language models meet knowledge graphs for question answering: Synthesis and opportunities. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (pp. 24589-24608).
• Han, H., Wang, Y., Shomer, H., Guo, K., Ding, J., Lei, Y., … & Tang, J. (2024). Retrieval-augmented generation with graphs (graphrag). arXiv preprint arXiv:2501.00309.
• Liu, B., Fang, Y., Xu, N., Hou, S., Li, X., & Li, Q. (2025). Large language models for knowledge graph embedding: A survey. Mathematics, 13(14), 2244.

Research Questions

• How are LLM-Agents defined, and what are their core characteristics?
• How have LLM and agents collaboration paradigms evolved in recent research?
• What are the main application areas and practical products of LLM-Agents today?
• Analyze the actual design concept of a typical agent product.?

Literature

• Own research
• Luo, J., Zhang, W., Yuan, Y., Zhao, Y., Yang, J., Gu, Y., … & Zhang, M. (2025). Large language model agent: A survey on methodology, applications and challenges. arXiv preprint arXiv:2503.21460.
• Yehudai, A., Eden, L., Li, A., Uziel, G., Zhao, Y., Bar-Haim, R., … & Shmueli-Scheuer, M. (2025). Survey on evaluation of llm-based agents. arXiv preprint arXiv:2503.16416.
• Mohammadi, M., Li, Y., Lo, J., & Yip, W. (2025, August). Evaluation and benchmarking of llm agents: A survey. In Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V. 2 (pp. 6129-6139).

Research Questions

• What is Green AI, and how is it different from traditional AI system design?
• How can system architecture models represent sustainability aspects such as energy efficiency, carbon footprint, and resource consumption?
• How can architectural modeling languages such as UML, SysML, or WAM be extended to include Green AI concerns?
• Show a small demo or conceptual model of a system architecture that includes Green AI metrics

Literature

• Own research
• https://doi.org/10.1016/j.neucom.2024.128096
• https://doi.org/10.1145/2578128.2578226

Research Questions

• What is Trustworthy AI? Why is Trustworthy AI important in system architecture?
• Which trustworthiness aspects can be represented in architecture models, such as fairness, explainability, privacy, or robustness?
• How can modeling languages such as UML, SysML, or WAM help describe Trustworthy AI systems?
• Show a small example of a system architecture model with Trustworthy AI aspects

Literature

• Own research

Research Questions

• What is cost modeling in the context of system or software architecture?
• Which methods exist to evaluate the cost and benefit of architectural alternatives?
• How can cost models be integrated into architecture modeling approaches such as UML, SysML, or WAM?
• Show a small example comparing two architectural designs using cost-related criteria

Literature

• Own research
• https://doi.org/10.1109/ICSE.2001.919103
• https://doi.org/10.1145/1810295.1810317
• https://doi.org/10.1016/C2012-0-02842-6

• What is the difference between qualitative and quantitative research methodologies?
• Provide an overview of different methodologies, explain how they work, when and in which field they are applied.
• Qualitative: Conduct a survey with researchers and professionals. Research on how to formulate survey questions and send them out to experts.
• Quantitative: Analyse existing datasets. Create search queries for databases and analyse the found datasets on specific aspects.
• Describe your methodologies in detail in a research log and note down any meetings, decisions, changes, and outcomes.
• Reflect on the differences in using both methodologies and provide insights into new learnings, pain points, and how you can apply the different methodologies you found in other areas.

Literature

• Own research
• Creswell, J. W. (2014). Research design : Qualitative, quantitative, and mixed methods approaches (4. ed., in). SAGE. https://katalog.bibliothek.tu-chemnitz.de/Record/0008891954
• Trochim, W., Donnelly, J. P., & Arora, K. (2016). Research methods: The essential knowledge base. Research methods: the essential knowledge base.

Research Questions

• What is the history of graphical user interfaces, conversational interfaces (specifically chatbots), and how do these inform the interfaces of LLMs? Research and provide a brief overview of the development of user interfaces.
• Conduct a systematic analysis of the interfaces from Large Language Models. For this, start with collecting at least 10 different providers from LLMs. Interact with these LLMs and record your interactions. Then start labeling the interactions of both partners regarding all available interface elements. Both students should do this on their own without talking about the results. Research on useful qualitative methods for this, like ‘Grounded Theory’.
• Compare your labeling, discuss differences together with your advisor and create a list of UI elements. Describe how they look, where they are located, what their function is, and other relevant criteria.
• Create a prototype on the stereotypical LLM interface and present it.
• Compare the interfaces of LLMs with other chatbots. Where do you find differences? How can you explain them?

Literature

• Own research
• Khan, R., Das, A. (2018). Introduction to Chatbots. In: Build Better Chatbots. Apress, Berkeley, CA. https://doi.org/10.1007/978-1-4842-3111-1_1
• Mohit Jain, Pratyush Kumar, Ramachandra Kota, and Shwetak N. Patel. 2018. Evaluating and Informing the Design of Chatbots. In Proceedings of the 2018 Designing Interactive Systems Conference (DIS ’18). Association for Computing Machinery, New York, NY, USA, 895–906. https://doi.org/10.1145/3196709.3196735
• Adamopoulou, E., & Moussiades, L. (2020). An overview of chatbot technology. In Artificial Intelligence Applications and Innovations: 16th IFIP WG 12.5 International Conference, AIAI 2020, Neos Marmaras, Greece, June 5–7, 2020, Proceedings, Part II 16 (pp. 373-383). Springer International Publishing. https://doi.org/10.1007/978-3-030-49186-4_31
• Traubinger, V., Gaedke, M. (2024). Interaction Design Patterns of Web Chatbots. In: Stefanidis, K., Systä, K., Matera, M., Heil, S., Kondylakis, H., Quintarelli, E. (eds) Web Engineering. ICWE 2024. Lecture Notes in Computer Science, vol 14629. Springer, Cham. https://doi.org/10.1007/978-3-031-62362-2_22
• Tidwell, J., Brewer, C., Valencia, A.: Designing Interfaces: Patterns for Effective Interaction Design. O’Reilly, Beijing [China]; North Sebastopol, CA, third edition edn. (2020) https://katalog.bibliothek.tu-chemnitz.de/Record/0-1684818338?sid=60672775
• Savin-Baden, M., & Major, C. H. (2025). Qualitative research: The essential guide to theory and practice. Routledge. https://katalog.bibliothek.tu-chemnitz.de/Record/0-1939098580?sid=60673159
• Anker Helms Jørgensen and Brad A. Myers. 2008. User interface history. In CHI ’08 Extended Abstracts on Human Factors in Computing Systems (CHI EA ’08). Association for Computing Machinery, New York, NY, USA, 2415–2418. https://doi.org/10.1145/1358628.1358696
• Traubinger, V., Heil, S., Grigera, J., Garrido, A., Abhyankar, S., Gaedke, M. (2025). An Analysis of Federal and Municipal Chatbots in Germany. In: Følstad, A., et al. Chatbots and Human-Centered AI. CONVERSATIONS 2024. Lecture Notes in Computer Science, vol 15545. Springer, Cham. https://doi.org/10.1007/978-3-031-88045-2_13

Research Questions

• What are different models for Object Detection? Explain at least 5 different models with understandable visualisations.
• How do these models differ from each other? Research a set of meaningful characteristics for this (method, necessary training size, hardware requirements, time for training/fine tuning, etc.)
• Prepare a dataset for fine tuning a selected model. You will receive a dataset of screenshots and recordings from your advisor which you should then use a basis. With the created dataset, you will then fine tune a model (access to hardware resources wil be given).
• Evaluate the fine tuned model and present the results. What are standard metrics and benchmarks for this?

Literature

• Own research
• Sapkota, R., & Karkee, M. (2026). Object detection with multimodal large vision-language models: An in-depth review. Information Fusion, 126, 103575. https://doi.org/10.1016/j.inffus.2025.103575
• Trigka, M., & Dritsas, E. (2025). A Comprehensive Survey of Machine Learning Techniques and Models for Object Detection. Sensors, 25(1), 214. https://doi.org/10.3390/s25010214
• Zaidi, S. S. A., Ansari, M. S., Aslam, A., Kanwal, N., Asghar, M., & Lee, B. (2022). A survey of modern deep learning based object detection models. Digital Signal Processing, 126, 103514. https://doi.org/10.1016/j.dsp.2022.103514

Research Questions

• Which laws and regulations affect the use of AI, and what do they demand? This includes AI-specific regulations, those that were updated to consider AI, and also regulations that only indirectly affect AI.
• Which guidelines and principles exist regarding the use of AI? How can they be implemented?
• Present your findings in form of an overview over the laws, regulations, guidelines and principles that are relevant when creating or using AI applications!

Literature

• Own research

Research Questions

• What is WebMCP? What opportunities does WebMCP offer? What are its limitations?
• What are Web Agents? Which approaches exist for creating Web Agents?
• Create a basic AI-based assistant for interacting with a web application using WebMCP!

Literature

• B. Walderman, K. Sagar, and D. Farolino, “WebMCP,” W3C Machine Learning Community Group, Mar. 2026. Available: https://webmachinelearning.github.io/webmcp
• L. Ning et al., “A Survey of WebAgents: Towards Next-Generation AI Agents for Web Automation with Large Foundation Models,” in Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2, in KDD ’25. Toronto ON, Canada: Association for Computing Machinery, 2025, pp. 6140–6150. doi: 10.1145/3711896.3736555. Available: https://doi.org/10.1145/3711896.3736555
• Own research

Research Questions

• What is a natural language interface for knowledge graphs?
• What methods exist to convert user questions into SPARQL queries?
• What role do large language models play in querying knowledge graphs?
• What are the main limitations of current approaches?
• What research challenges remain open?

Literature

• Own Research
• K. Affolter, K. Stockinger, and A. Bernstein, “A Comparative Survey of Recent Natural Language Interfaces for Databases,” VLDB J., vol. 28, no. 5, pp. 793–819, 2019, doi: https://doi.org/10.1007/s00778-019-00573-y
• X. Pan et al., “Unifying Large Language Models and Knowledge Graphs: A Roadmap,” IEEE Trans. Knowl. Data Eng., vol. 36, no. 7, pp. 3580–3599, 2024, doi: https://doi.org/10.1109/TKDE.2024.3352100
• C. Ma, Y. Chen, T. Wu, A. Khan, and H. Wang, “Large Language Models Meet Knowledge Graphs for Question Answering: Synthesis and Opportunities,” in Proc. Conf. Empirical Methods Natural Language Processing (EMNLP), 2025, pp. 24578–24597. [Online]. Available: https://aclanthology.org/2025.emnlp-main.1249/
• A. Hogan et al., “Knowledge Graphs,” ACM Comput. Surv., vol. 54, no. 4, pp. 1–72, 2021, doi: https://doi.org/10.1145/3447772

Research Questions

• What is knowledge graph construction?
• How can LLMs be used to build knowledge graphs from text?
• What are the main methods used (e.g., prompting, fine-tuning)?
• What are the main quality problems (e.g., hallucination, wrong facts)?
• What research challenges remain open?

Literature

• Own research
• A. Ghanem and C. Cruz, “Fine-Tuning or Prompting on LLMs: Evaluating Knowledge Graph Construction Task,” Frontiers in Big Data, vol. 8, Art. no. 1505877, Jun. 2025, doi: https://doi.org/10.3389/fdata.2025.1505877
• X. Pan et al., “Unifying Large Language Models and Knowledge Graphs: A Roadmap,” IEEE Trans. Knowl. Data Eng., vol. 36, no. 7, pp. 3580–3599, 2024, doi: https://doi.org/10.1109/TKDE.2024.3352100
• B. Zhang and H. Soh, “Extract, Define, Canonicalize: An LLM-Based Framework for Knowledge Graph Construction,” in Proc. Conf. Empirical Methods Natural Language Processing (EMNLP), 2024, pp. 9820–9836. [Online]. Available: https://aclanthology.org/2024.emnlp-main.548/
• A. Hogan et al., “Knowledge Graphs,” ACM Comput. Surv., vol. 54, no. 4, pp. 1–72, 2021, doi: https://doi.org/10.1145/3447772

Research Questions

• What is SHACL, and what problem does it solve?
• How does SHACL use shapes to validate RDF data?
• What tools are available for SHACL validation?
• How does SHACL compare to ShEx?
• What are the main open challenges?

Literature

• Own research
• H. Knublauch and D. Kontokostas, “Shapes Constraint Language (SHACL),” W3C Recommendation, Jul. 2017. [Online]. Available: https://www.w3.org/TR/shacl/
• K. Rabbani, M. Lissandrini, and K. Hose, “SHACL and ShEx in the Wild: A Community Survey on Validating Shapes Generation and Adoption,” in Proc. ACM Web Conf. (WWW), 2022, pp. 260–263, doi: https://doi.org/10.1145/3487553.3524253
• J. E. Labra Gayo, E. Prud’hommeaux, I. Boneva, and D. Kontokostas, Validating RDF Data. San Rafael, CA, USA: Morgan and Claypool, 2018. [Online]. Available: https://book.validatingrdf.com/
• K. Rabbani, M. Lissandrini, and K. Hose, “Extraction of Validating Shapes from Very Large Knowledge Graphs,” Proc. VLDB Endowment, vol. 16, no. 5, pp. 1023–1032, 2023, doi: https://doi.org/10.14778/3579075.3579078

Research Questions

• What are the main methodologies for ontology construction (manual, semi-automatic, automatic), and how have they evolved over time?
• How has ontology evolution (versioning, alignment, and change management) been addressed in dynamic knowledge environments?
• How do top-down vs. bottom-up ontology construction approaches impact scalability, accuracy, and domain adaptability?
• What role do ontology languages (e.g., OWL, RDF) and formal logic play in ensuring interoperability and reasoning capabilities?
• What are the emerging trends in ontology learning using AI/LLMs, and how do they affect ontology quality and maintenance?

Literature

• Own research
• Ontology Learning and Knowledge Graph Construction: A Comparison of Approaches and Their Impact on RAG Performance, Tiago da Cruz, Bernardo Tavares, Francisco Belo, https://doi.org/10.48550/arXiv.2511.05991

Research Questions

• What are the common patterns and causes of fabricated or hallucinated references in academic writing and AI-generated content?
• What automated methods can detect fake references (e.g., citation graph analysis, metadata validation, DOI verification)?
• How can external authority systems (CrossRef, ORCID, Scopus) be used to validate authors and publications? What role do knowledge graphs and bibliographic databases play in detecting inconsistencies and fraud? How can machine learning and LLM-based systems be used both to detect and to prevent fabricated citations?

Literature

• Own research
• CheckIfExist: Detecting Citation Hallucinations in the Era of AI-Generated Content. https://doi.org/10.48550/arXiv.2602.15871
• https://github.com/hadipourh/verifyref

Research Questions

• What are the standard pipelines for knowledge graph construction (data extraction, integration, fusion, refinement)?
• How do ontology-driven vs. schema-less knowledge graphs differ in design and application?
• How has knowledge graph construction evolved from rule-based systems to machine learning and LLM-based approaches?

Literature

• Own research
• Aidan Hogan et al. (2021). Knowledge Graphs.
• LLM-empowered knowledge graph construction: A survey. Haonan Bian.
  https://doi.org/10.48550/arXiv.2510.20345

Research Questions

• Introduction: In modern research infrastructures, isolated data silos hinder seamless knowledge exchange. Here ontology mappings come into play, like mappings to the Basic Formal Ontology (BFO) for philosophically grounded semantic interoperability, OpenAIRE for pragmatic integration within the European Open Science Cloud ecosystem, and the Kerndatensatz Forschung (KDSF) as a core metadata standard for research data.
• What are the primary purposes and fundamental concepts of BFO, Openaire, and KDSF? How do these frameworks shape the European research and education data ecosystem?
• What approaches and best practices exist for amending an existing ontology to achieve conformance with BFO, Openaire, and KDSF standards? What challenges arise in this process?
• In the context of the Across ontology as a use case, how can it be systematically mapped to BFO, Openaire, and KDSF?
• Prepare a comprehensive mapping document for the Across ontology mapping.

Literature

• ISO/IEC 21838-2:2021, Top-level Ontologies – Part 2: Basic Formal Ontology (BFO). International Organization for Standardization, 2021. Online. Available: https://www.iso.org/standard/74572.html
• OpenAIRE Guidelines — Release 3.0, OpenAIRE, 2019. Online. Available: https://guidelines.openaire.eu/en/latest/
• Kerndatensatz Forschung (KDFS) – Offizielle Spezifikationen. Online. Available: https://www.kerndatensatz-forschung.de
• Own research