Soft Begging: Modular and Efficient Shielding of LLMs against Prompt Injection and Jailbreaking based on Prompt Tuning S Ostermann, K Baum, C Endres, J Masloh, P Schramowski arXiv preprint arXiv:2407.03391, 2024 | | 2024 |
On the Quest for Effectiveness in Human Oversight: Interdisciplinary Perspectives S Sterz, K Baum, S Biewer, H Hermanns, A Lauber-Rönsberg, P Meinel, ... The 2024 ACM Conference on Fairness, Accountability, and Transparency, 2495-2507, 2024 | | 2024 |
Software doping analysis for human oversight S Biewer, K Baum, S Sterz, H Hermanns, S Hetmank, M Langer, ... Formal Methods in System Design, 1-50, 2024 | 4 | 2024 |
A signal detection perspective on error and unfairness detection as a critical aspect of human oversight of AI-based systems M Langer, K Baum, N Schlicker OSF, 2023 | | 2023 |
XAI requirements in smart production processes: a case study D Baum, K Baum, TP Gros, V Wolf World Conference on Explainable Artificial Intelligence, 3-24, 2023 | 4 | 2023 |
From fear to action: AI governance and opportunities for all K Baum, J Bryson, F Dignum, V Dignum, M Grobelnik, H Hoos, M Irgens, ... Frontiers in Computer Science 5, 1210421, 2023 | 9 | 2023 |
A micro and macro perspective on trustworthiness: theoretical underpinnings of the Trustworthiness Assessment Model (TrAM) N Schlicker, K Baum, A Uhde, S Sterz, MC Hirsch, M Langer PsyArXiv, 2022 | 2 | 2022 |
Calibrated trust as a result of accurate trustworthiness assessment–Introducing the trustworthiness assessment model N Schlicker, A Uhde, K Baum, MC Hirsch, M Langer PsyArXiv, 2022 | 7 | 2022 |
Ethics for Nerds K Baum, S Sterz The International Review of Information Ethics 31 (1), 2022 | | 2022 |
From responsibility to reason-giving explainable artificial intelligence K Baum, S Mantel, E Schmidt, T Speith Philosophy & Technology 35 (1), 12, 2022 | 62 | 2022 |
Towards perspicuity requirements S Sterz, K Baum, A Lauber-Rönsberg, H Hermanns 2021 IEEE 29th International Requirements Engineering Conference Workshops …, 2021 | 10 | 2021 |
Explainability auditing for intelligent systems: a rationale for multi-disciplinary perspectives M Langer, K Baum, K Hartmann, S Hessel, T Speith, J Wahl 2021 IEEE 29th international requirements engineering conference workshops …, 2021 | 29 | 2021 |
What to expect from opening up ‘black boxes’? Comparing perceptions of justice between human and automated agents N Schlicker, M Langer, SK Ötting, K Baum, CJ König, D Wallach Computers in Human Behavior 122, 106837, 2021 | 75 | 2021 |
What do we want from Explainable Artificial Intelligence (XAI)?–A stakeholder perspective on XAI and a conceptual model guiding interdisciplinary XAI research M Langer, D Oster, T Speith, H Hermanns, L Kästner, E Schmidt, A Sesing, ... Artificial Intelligence 296, 103473, 2021 | 430 | 2021 |
Spare me the details: How the type of information about automated interviews influences applicant reactions M Langer, K Baum, CJ König, V Hähne, D Oster, T Speith International Journal of Selection and Assessment 29 (2), 154-169, 2021 | 43 | 2021 |
"Have you ever questioned the nature of your reality?“ — Westworld aus der Perspektive der Philosophie M Schillo, K Baum Folge um Folge. Multiple Perspektiven auf die Fernsehserie, 263-279, 2020 | | 2020 |
Algorithmen und die Grenzen von Fairness K Baum, T Feldkamp, S Henning, N Käfer Unternehmensverantwortung im digitalen Wandel: Ein Debattenbeitrag zu …, 2020 | 2 | 2020 |
Explainability as a non-functional requirement MA Köhl, K Baum, M Langer, D Oster, T Speith, D Bohlender 2019 IEEE 27th International Requirements Engineering Conference (RE), 363-368, 2019 | 115 | 2019 |
Towards a framework combining machine ethics and machine explainability K Baum, H Hermanns, T Speith arXiv preprint arXiv:1901.00590, 2019 | 14 | 2019 |
Anforderungen an die Erklärbarkeit maschinengestützter Entscheidungen A Sesing, K Baum Tagungsband DSRI-Herbstakademie: Die Macht der Daten und der Algorithmen …, 2019 | | 2019 |