Fostering effective hybrid human-LLM reasoning and decision making.

The impressive performance of modern Large Language Models (LLMs) across a wide range of tasks, along with their often non-trivial errors, has garnered unprecedented attention regarding the potential of AI and its impact on everyday life. While considerable effort has been and continues to be dedicated to overcoming the limitations of current models, the potentials and risks of human-LLM collaboration remain largely underexplored. In this perspective, we argue that enhancing the focus on human-LLM interaction should be a primary target for future LLM research.

IRF-1 Regulates Mitochondrial Respiration and Intrinsic Apoptosis Under Metabolic Stress through ATP Synthase Ancillary Factor TMEM70.

Mitochondrial dysfunction, which can be caused by metabolic stressors such as oxidized low-density lipoprotein (oxLDL), sensitizes the endothelium to pathological changes. The transcription factor interferon regulatory factor 1 (IRF-1) is a master regulator of inflammation, previously shown to promote oxLDL-induced inflammatory pyroptosis in human aortic endothelial cells (HAEC). However, a presumed role for IRF-1 in regulating the intrinsic apoptotic pathway in response to metabolic stress has not been demonstrated.

Personalized bundle recommendation using preference elicitation and the Choquet integral.

Bundle recommendation aims to generate bundles of associated products that users tend to consume as a whole under certain circumstances. Modeling the bundle utility for users is a non-trivial task, as it requires to account for the potential interdependencies between bundle attributes. To address this challenge, we introduce a new preference-based approach for bundle recommendation exploiting the Choquet integral.

Interpretability Is in the Mind of the Beholder: A Causal Framework for Human-Interpretable Representation Learning.

Research on Explainable Artificial Intelligence has recently started exploring the idea of producing explanations that, rather than being expressed in terms of low-level features, are encoded in terms of . How to reliably acquire such concepts is, however, still fundamentally unclear. An agreed-upon notion of concept interpretability is missing, with the result that concepts used by both post hoc explainers and neural networks are acquired through a variety of mutually incompatible strategies.

Interactions between pea protein and gellan gum for the development of plant-based structures.

Plant-based analogs have been developed to mimic foods from animal sources by using ingredients from vegetable sources. Among the strategies to produce plant-based structures is the gelation of mixtures between plant proteins and polysaccharides. In this study, our aim was to investigate gels of pea proteins and gellan gum with high protein concentration and the addition of salt (potassium and sodium chloride).