Related papers: Earning Extra Performance from Restrictive Feedbac…

Reward models (RMs) are essential for aligning Large Language Models (LLMs) with human preferences. However, they often struggle with capturing complex human preferences and generalizing to unseen data. To address these challenges, we…

Earnings calls are a key source of financial information about public companies. However, extracting information from these calls is difficult. Unlike the templatic filings required by the U.S. Securities and Exchange Commission (SEC) to…

Standard fine-tuning is considered not as effective as specialized methods for model editing due to its comparatively poor performance. However, it is simple, agnostic to the architectural details of the model being edited, and able to…

Addressing the challenge of low-resource information extraction remains an ongoing issue due to the inherent information scarcity within limited training examples. Existing data augmentation methods, considered potential solutions, struggle…

Aligning large language models (LLMs) with human preferences is essential for safe and useful LLMs. Previous works mainly adopt reinforcement learning (RLHF) and direct preference optimization (DPO) with human feedback for alignment.…

Non-independent and identically distributed (Non-IID) data across edge clients have long posed significant challenges to federated learning (FL) training in edge computing environments. Prior works have proposed various methods to mitigate…

The ability to train generative models that produce realistic, safe and useful tabular data is essential for data privacy, imputation, oversampling, explainability or simulation. However, generating tabular data is not straightforward due…

Transformer models have emerged as potent solutions to a wide array of multidisciplinary challenges. The deployment of Transformer architectures is significantly hindered by their extensive computational and memory requirements,…

In performative prediction, the deployment of a predictive model triggers a shift in the data distribution. As these shifts are typically unknown ahead of time, the learner needs to deploy a model to get feedback about the distribution it…

Studies have shown that modern neural networks tend to be poorly calibrated due to over-confident predictions. Traditionally, post-processing methods have been used to calibrate the model after training. In recent years, various trainable…

When predictions are performative, the choice of which predictor to deploy influences the distribution of future observations. The overarching goal in learning under performativity is to find a predictor that has low \emph{performative…

For deep learning practitioners, hyperparameter tuning for optimizing model performance can be a computationally expensive task. Though visualization can help practitioners relate hyperparameter settings to overall model performance,…

Machine learning models trained on real-world data may inadvertently make biased predictions that negatively impact marginalized communities. Reweighting, which assigns a weight to each data point used during model training, can mitigate…

It remains a challenging problem to tightly estimate the worst case response time of an application in a distributed embedded system, especially when there are dependencies between tasks. We discovered that the state-of-the art techniques…

Despite the promise of RLHF in aligning LLMs with human preferences, it often leads to superficial alignment, prioritizing stylistic changes over improving downstream performance of LLMs. Underspecified preferences could obscure directions…

Parameter fine tuning is a transfer learning approach whereby learned parameters from pre-trained source network are transferred to the target network followed by fine-tuning. Prior research has shown that this approach is capable of…

Models that top leaderboards often perform unsatisfactorily when deployed in real world applications; this has necessitated rigorous and expensive pre-deployment model testing. A hitherto unexplored facet of model performance is: Are our…

Mixed-effects regression models represent a useful subclass of regression models for grouped data; the introduction of random effects allows for the correlation between observations within each group to be conveniently captured when…

To effect behavior change a successful algorithm must make high-quality decisions in real-time. For example, a mobile health (mHealth) application designed to increase physical activity must make contextually relevant suggestions to…

Reinforcement learning has been widely applied in automated bidding. Traditional approaches model bidding as a Markov Decision Process (MDP). Recently, some studies have explored using generative reinforcement learning methods to address…