Related papers: How much baseline correction do we need in ERP res…
Reinforcement learning (RL) with outcome-based rewards has proven effective for improving large language models (LLMs) on complex reasoning tasks. However, its success often depends on the base model occasionally sampling correct solutions.…
Understanding the uncertainty of a neural network's (NN) predictions is essential for many purposes. The Bayesian framework provides a principled approach to this, however applying it to NNs is challenging due to large numbers of parameters…
Large reasoning models (LRMs) substantially outperform their base LLM counterparts on challenging reasoning benchmarks, yet it remains poorly understood where base models go wrong during token-by-token generation and how to narrow this gap…
Imbalanced classification and spurious correlation are common challenges in data science and machine learning. Both issues are linked to data imbalance, with certain groups of data samples significantly underrepresented, which in turn would…
Knowledge editing aims to update the embedded knowledge within Large Language Models (LLMs). However, existing approaches, whether through parameter modification or external memory integration, often suffer from inconsistent evaluation…
Retrieval-Augmented Generation (RAG) enhances factual grounding in large language models (LLMs) by incorporating retrieved evidence, but LLM accuracy declines when long or noisy contexts exceed the model's effective attention span. Existing…
The application of large language models (LLMs) in recommendation systems has recently gained traction. Traditional recommendation systems often lack explainability and suffer from issues such as popularity bias. Previous research has also…
Model-based reinforcement learning promises to learn an optimal policy from fewer interactions with the environment compared to model-free reinforcement learning by learning an intermediate model of the environment in order to predict…
Empirical Bayes estimators are based on minimizing the average risk with the hyper-parameters in the weighting function being estimated from observed data. The performance of an empirical Bayes estimator is typically evaluated by its mean…
An adjustable algorithm of exclusion of conditional equations with excessive residuals is proposed. The criteria applied in the algorithm use variable exclusion limits which decrease as the number of equations goes down. The algorithm is…
Currently, machine learning (ML) methods are widely used to process the results of physical experiments. In some cases, due to the limited amount of experimental data, ML-models can be pre-trained on synthetic data simulated based on the…
Building explainable systems is a critical problem in the field of Natural Language Processing (NLP), since most machine learning models provide no explanations for the predictions. Existing approaches for explainable machine learning…
Improving the accessibility of psychotherapy with the aid of Large Language Models (LLMs) is garnering a significant attention in recent years. Recognizing cognitive distortions from the interviewee's utterances can be an essential part of…
Model checking is essential to evaluate the adequacy of statistical models and the validity of inferences drawn from them. Particularly, hierarchical models such as latent Gaussian models (LGMs) pose unique challenges as it is difficult to…
The generalized Gauss-Newton (GGN) approximation is often used to make practical Bayesian deep learning approaches scalable by replacing a second order derivative with a product of first order derivatives. In this paper we argue that the…
Objective: Large language models (LLMs) are attracting increasing interest in healthcare. This commentary evaluates the potential of LLMs to improve clinical prediction models (CPMs) for diagnostic and prognostic tasks, with a focus on…
The accuracy of Bayesian inference can be negatively affected by the use of inaccurate forward models. In the case of gravitational-wave inference, accurate but computationally expensive waveform models are sometimes substituted with faster…
Large language models (LLMs) are increasingly optimized for long reasoning, under the assumption that more reasoning leads to better performance. However, emerging evidence suggests that longer responses can sometimes degrade accuracy…
We show that current open-source foundational LLMs possess instruction capability and German legal background knowledge that is sufficient for some legal analysis in an educational context. However, model capability breaks down in very…
In transfer learning, the learner leverages auxiliary data to improve generalization on a main task. However, the precise theoretical understanding of when and how auxiliary data help remains incomplete. We provide new insights on this…