arXiv subjects

Viktor Kewenig

Publications and source records attributed to Viktor Kewenig.

5 recordsLinked to original sources

arXiv2026

From Binary Groundedness to Support Relations: Towards a Reader-Centred Taxonomy for Comprehension of AI Output

Generative AI tools often answer questions using source documents, e.g., through retrieval augmented generation. Current groundedness and hallucination evaluations largely frame the relationship between an answer and its sources as binary (the answer is either supported or unsupported). However, this obscures both the syntactic moves (e.g., direct quotation vs. paraphrase) and the interpretive moves (e.g., induction vs. deduction) performed when models reformulate evidence into an answer. This limits both benchmarking and user-facing provenance interfaces. We propose the development of a reader-centred taxonomy of grounding as a set of support relations between generated statements and source documents. We explain how this might be synthesised from prior research in linguistics and philosophy of language, and evaluated through a benchmark and human annotation protocol. Such a framework would enable interfaces that communicate not just whether a claim is grounded, but how.

cs.HC↗

arXiv2025

The New Calculator? Practices, Norms, and Implications of Generative AI in Higher Education

Generative AI (GenAI) has introduced myriad opportunities and challenges for higher education. Anticipating this potential transformation requires understanding students' contextualised practices and norms around GenAI. We conducted semi-structured interviews with 26 students and 11 educators from diverse departments across two universities. Grounded in Strong Structuration Theory, we find diversity in students' uses and motivations for GenAI. Occurring in the context of unclear university guidelines, institutional fixation on plagiarism, and inconsistent educator communication, students' practices are informed by unspoken rules around appropriate use, GenAI limitations and reliance strategies, and consideration of agency and skills. Perceived impacts include changes in confidence, and concerns about skill development, relationships with educators, and plagiarism. Both groups envision changes in universities' attitude to GenAI, responsible use training, assessments, and integration of GenAI into education. We discuss socio-technical implications in terms of current and anticipated changes in the external and internal structures that contextualise students' GenAI use.

cs.HC↗

arXiv2024

The Metacognitive Demands and Opportunities of Generative AI

Generative AI (GenAI) systems offer unprecedented opportunities for transforming professional and personal work, yet present challenges around prompting, evaluating and relying on outputs, and optimizing workflows. We argue that metacognition$\unicode{x2013}$the psychological ability to monitor and control one's thoughts and behavior$\unicode{x2013}$offers a valuable lens to understand and design for these usability challenges. Drawing on research in psychology and cognitive science, and recent GenAI user studies, we illustrate how GenAI systems impose metacognitive demands on users, requiring a high degree of metacognitive monitoring and control. We propose these demands could be addressed by integrating metacognitive support strategies into GenAI systems, and by designing GenAI systems to reduce their metacognitive demand by targeting explainability and customizability. Metacognition offers a coherent framework for understanding the usability challenges posed by GenAI, and provides novel research and design directions to advance human-AI interaction.

cs.HC↗

arXiv2024

Ironies of Generative AI: Understanding and mitigating productivity loss in human-AI interactions

Generative AI (GenAI) systems offer opportunities to increase user productivity in many tasks, such as programming and writing. However, while they boost productivity in some studies, many others show that users are working ineffectively with GenAI systems and losing productivity. Despite the apparent novelty of these usability challenges, these 'ironies of automation' have been observed for over three decades in Human Factors research on the introduction of automation in domains such as aviation, automated driving, and intelligence. We draw on this extensive research alongside recent GenAI user studies to outline four key reasons for productivity loss with GenAI systems: a shift in users' roles from production to evaluation, unhelpful restructuring of workflows, interruptions, and a tendency for automation to make easy tasks easier and hard tasks harder. We then suggest how Human Factors research can also inform GenAI system design to mitigate productivity loss by using approaches such as continuous feedback, system personalization, ecological interface design, task stabilization, and clear task allocation. Thus, we ground developments in GenAI system usability in decades of Human Factors research, ensuring that the design of human-AI interactions in this rapidly moving field learns from history instead of repeating it.

cs.HC↗

arXiv2023

Attention, not scale, drives human-AI alignment in multimodal language prediction

Humans routinely draw on visual context to predict upcoming words. To what extent current vision-language models produce comparable behaviour is unclear. Here we placed five state-of-the-art pretrained systems side-by-side with 600 human participants in a web-based Visual-World Paradigm. On each of 100 six-second movie clips, models and participants received either text only or synchronised video and text and judged how likely a specified target word was to appear next; human eye movements were tracked throughout. Adding visual context increased model-human alignment in predictability ratings across all architectures (average Delta r = 0.18) with no impact of parameter size. When visual context was informative, transformer attention significantly increased alignment. Attention maps from two transformer models corresponded with human gaze, explaining up to 70% of the inter-participant variance when the scene contained informative cues. Notably, cross-modal attention reliably tracked anticipatory human fixations on semantic cues. These results suggest that current transformer-based vision-language models can approximate human behaviour exploiting visual context during language prediction - and that selective attention to informative cues, not sheer model scale, is the principal driver of this alignment.

cs.AI↗