Evaluating language models for mathematics through interactions.

There is much excitement about the opportunity to harness the power of large language models (LLMs) when building problem-solving assistants. However, the standard methodology of evaluating LLMs relies on static pairs of inputs and outputs; this is insufficient for making an informed decision about which LLMs are best to use in an interactive setting, and how that varies by setting. Static assessment therefore limits how we understand language model capabilities.

Analyzing global utilization and missed opportunities in debt-for-nature swaps with generative AI.

We deploy a prompt-augmented GPT-4 model to distill comprehensive datasets on the global application of debt-for-nature swaps (DNS), a pivotal financial tool for environmental conservation. Our analysis includes 195 nations and identifies 21 countries that have not yet used DNS before as prime candidates for DNS. A significant proportion demonstrates consistent commitments to conservation finance (0.

Associative Memories via Predictive Coding.

Associative memories in the brain receive and store patterns of activity registered by the sensory neurons, and are able to retrieve them when necessary. Due to their importance in human intelligence, computational models of associative memories have been developed for several decades now. In this paper, we present a novel neural model for realizing associative memories, which is based on a hierarchical generative network that receives external stimuli via sensory neurons.

Glycation Leads to Increased Polysialylation and Promotes the Metastatic Potential of Neuroblastoma Cells.

Neuroblastoma is the second most frequent extracranial tumor, affecting young children worldwide. One hallmark of tumors such as neuroblastomas, is the expression of polysialic acid, which interferes with adhesion and may promote invasion and metastasis. Since tumor cells use glycolysis for energy production, they thereby produce as side product methylglyoxal (MGO), which reacts with proteins to advanced glycation end products in a mechanism called glycation.

Increased Expression of Immature Mannose-Containing Glycoproteins and Sialic Acid in Aged Mouse Brains.

Aging represents the accumulation of changes in an individual over time, encompassing physical, psychological, and social changes. Posttranslational modifications of proteins such as glycosylation, including sialylation or glycation, are proposed to be involved in this process, since they modulate a variety of molecular and cellular functions. In this study, we analyzed selected posttranslational modifications and the respective proteins on which they occur in young and old mouse brains.