Generative AI systems optimized for efficient artifact production can inadvertently bypass the cognitive labor that gives knowledge work its value. Through a Research through Design study in corporate goal-setting—a reflective practice increasingly hollowed by bureaucratic pressures—we propose and evaluate a design principle: cognitive outcomes first, material artifacts second. We operationalize this through a prototype using cognitive scaffolds that require users to articulate contextual nuances, constraints, and strategic realities before generating artifacts. Evaluation with 16 employees revealed that 75% recognized persistent questioning as productive rigor yielding “cognitive delta” (new insight). A five-month follow-up confirmed durability of cognitive outcomes beyond the study context. We contribute: (1) Cognitive outcomes first, a principle establishing cognitive labor as the primary product and artifacts as proof of work; (2) Instrumental drift, an analytic lens revealing how efficiency-optimized AI decouples instruments from purposes; and (3) empirical demonstration that persistent inquiry succeeds when designed for cognitive engagement, with users recognizing epistemic value despite interaction costs.

Current research in automatic summarisation is unapologetically anglo-centered-a persistent state-of-affairs, which also predates neural net approaches.High-quality automatic summarisation datasets are notoriously expensive to create, posing a challenge for any language.However, with digitalisation, archiving, and social media advertising of newswire articles, recent work has shown how, with careful methodology application, large-scale datasets can now be simply gathered instead of written.In this paper, we present a large-scale multilingual summarisation dataset containing articles in 92 languages, spread across 28.8 million articles, in more than 35 writing scripts.This is both the largest, most inclusive, existing automatic summarisation dataset, as well as one of the largest, most inclusive, ever published datasets for any NLP task.We present the first investigation on the efficacy of resource building from news platforms in the low-resource language setting.Finally, we provide some first insight on how low-resource language settings impact state-of-the-art automatic summarisation system performance.

Dataset development for automatic summarisation systems is notoriously English-oriented. In this paper we present the first large-scale non-English language dataset specifically curated for automatic summarisation. The document-summary pairs are news articles and manually written summaries in the Danish language. There has previously been no work done to establish a Danish summarisation dataset, nor any published work on the automatic summarisation of Danish. We provide therefore the first automatic summarisation dataset for the Danish language (large-scale or otherwise). To support the comparison of future automatic summarisation systems for Danish, we include system performance on this dataset of strong well-established unsupervised baseline systems, together with an oracle extractive summariser, which is the first account of automatic summarisation system performance for Danish. Finally, we make all code for automatically acquiring the data freely available and make explicit how this technology can easily be adapted in order to acquire automatic summarisation datasets for further languages.

Consider two competitive machine learning models, one of which was considered state-of-the art, and the other a competitive baseline.Suppose that by just permuting the examples of the training set, say by reversing the original order, by shuffling, or by mini-batching, you could report substantially better/worst performance for the system of your choice, by multiple percentage points.In this paper, we illustrate this scenario for a trending NLP task: Natural Language Inference (NLI).We show that for the two central NLI corpora today, the learning process of neural systems is far too sensitive to permutations of the data.In doing so we reopen the question of how to judge a good neural architecture for NLI, given the available dataset and perhaps, further, the soundness of the NLI task itself in its current state.