Related papers: Epistemic diversity across language models mitigat…

Output diversity is crucial for Large Language Models as it underpins pluralism and creativity. In this work, we reveal that controlling the language used during model thinking-the language of thought-provides a novel and structural source…

A fundamental challenge in developing data-driven approaches to ecological systems for tasks such as state estimation and prediction is the paucity of the observational or measurement data. For example, modern machine-learning techniques…

Language is far more than a communication tool. A wealth of information - including but not limited to the identities, psychological states, and social contexts of its users - can be gleaned through linguistic markers, and such insights are…

Diffusion models have seen immense success in modelling continuous data across a range of domains such as vision and audio. Despite the challenges of adapting diffusion models to discrete data, recent work explores their application to text…

Recent Machine Learning (ML) approaches have shown increased performance on benchmarks but at the cost of escalating computational demands. Hardware, algorithmic and carbon optimizations have been proposed to curb energy consumption and…

Ecological networks describe the interactions between different species, informing us of how they rely on one another for food, pollination and survival. If a species in an ecosystem is under threat of extinction, it can affect other…

A persistent skill library allows language model agents to reuse successful strategies across tasks. Maintaining such a library requires three coupled capabilities. The agent selects a relevant skill, utilizes it during execution, and…

Collective intelligence is the ability of a group to perform more effectively than any individual alone. Diversity among group members is a key condition for the emergence of collective intelligence, but maintaining diversity is challenging…

What scaling limits govern neural network training dynamics when model size and training time grow in tandem? We show that despite the complex interactions between architecture, training algorithms, and data, compute-optimally trained…

While preliminary findings indicate that multilingual LLMs exhibit reduced bias compared to monolingual ones, a comprehensive understanding of the effect of multilingual training on bias mitigation, is lacking. This study addresses this gap…

Biodiversity loss driven by agricultural intensification is a pressing global issue, with significant implications for ecosystem stability and human well-being. Existing policy instruments have so far proven insufficient in halting this…

With the continuous development of technological and educational innovation, learners nowadays can obtain a variety of support from agents such as teachers, peers, education technologies, and recently, generative artificial intelligence…

Recent language models achieve impressive results in tasks involving complex multistep reasoning, but scaling these capabilities further traditionally requires expensive collection of more annotated data. In this work, we explore the…

The subpopulationtion shift, characterized by a disparity in subpopulation distributibetween theween the training and target datasets, can significantly degrade the performance of machine learning models. Current solutions to subpopulation…

Healthcare clinics regularly encounter dynamic data that changes due to variations in patient populations, treatment policies, medical devices, and emerging disease patterns. Deep learning models can suffer from catastrophic forgetting when…

The proliferation of generative models, combined with pretraining on web-scale data, raises a timely question: what happens when these models are trained on their own generated outputs? Recent investigations into model-data feedback loops…

Large-scale generative models have shown impressive image-generation capabilities, propelled by massive data. However, this often inadvertently leads to the generation of harmful or inappropriate content and raises copyright concerns.…

Current trends in pre-training Large Language Models (LLMs) primarily focus on the scaling of model and dataset size. While the quality of pre-training data is considered an important factor for training powerful LLMs, it remains a nebulous…

As the diversity of people in higher education grows, Universities are struggling to provide inclusive environments that nurture the spirit of free inquiry in the presence of these differences. At the extreme, the value of diversity is…

Deep learning classifiers are assisting humans in making decisions and hence the user's trust in these models is of paramount importance. Trust is often a function of constant behavior. From an AI model perspective it means given the same…