Related papers: Leveraging Variation Theory in Counterfactual Data…
As humans increasingly rely on multiround conversational AI for high stakes decisions, principled frameworks are needed to ensure such interactions reliably improve decision quality. We adopt a human centric view governed by two principles:…
Counterfactual reasoning from logged data has become increasingly important for many applications such as web advertising or healthcare. In this paper, we address the problem of learning stochastic policies with continuous actions from the…
Active learning promises to improve annotation efficiency by iteratively selecting the most important data to be annotated first. However, we uncover a striking contradiction to this promise: active learning fails to select data as…
Active learning (AL) is for optimizing the selection of unlabeled data for annotation (labeling), aiming to enhance model performance while minimizing labeling effort. The key question in AL is which unlabeled data should be selected for…
While textual frequency has been validated as relevant to human cognition in reading speed, its relatedness to Large Language Models (LLMs) is seldom studied. We propose a novel research direction in terms of textual data frequency, which…
For text classification tasks, finetuned language models perform remarkably well. Yet, they tend to rely on spurious patterns in training data, thus limiting their performance on out-of-distribution (OOD) test data. Among recent models…
Auxiliary Learning (AL) is a form of multi-task learning in which a model trains on auxiliary tasks to boost performance on a primary objective. While AL has improved generalization across domains such as navigation, image classification,…
While AI algorithms have shown remarkable success in various fields, their lack of transparency hinders their application to real-life tasks. Although explanations targeted at non-experts are necessary for user trust and human-AI…
Reinforcement Learning from Human Feedback (RLHF) has become the standard for aligning Large Language Models (LLMs), yet its efficacy is bottlenecked by the high cost of acquiring preference data, especially in low-resource and expert…
We propose a new active learning (AL) method for text classification with convolutional neural networks (CNNs). In AL, one selects the instances to be manually labeled with the aim of maximizing model performance with minimal effort. Neural…
Counterfactual reasoning, a fundamental aspect of human cognition, involves contemplating alternatives to established facts or past events, significantly enhancing our abilities in planning and decision-making. In light of the advancements…
Developed to alleviate prohibitive labeling costs, active learning (AL) methods aim to reduce label complexity in supervised learning. While recent work has demonstrated the benefit of using AL in combination with large pre-trained language…
Aligning large language models (LLMs) depends on high-quality datasets of human preference labels, which are costly to collect. Although active learning has been studied to improve sample efficiency relative to passive collection, many…
Conventional methods for query autocompletion aim to predict which completed query a user will select from a list. A shortcoming of this approach is that users often do not know which query will provide the best retrieval performance on the…
Data augmentation is an essential part of the training process applied to deep learning models. The motivation is that a robust training process for deep learning models depends on large annotated datasets, which are expensive to be…
Despite alarm over the reliance of machine learning systems on so-called spurious patterns, the term lacks coherent meaning in standard statistical frameworks. However, the language of causality offers clarity: spurious associations are due…
Modern systems that rely on Machine Learning (ML) for predictive modelling, may suffer from the cold-start problem: supervised models work well but, initially, there are no labels, which are costly or slow to obtain. This problem is even…
To collaborate well with robots, we must be able to understand their decision making. Humans naturally infer other agents' beliefs and desires by reasoning about their observable behavior in a way that resembles inverse reinforcement…
Despite recent advancements, NLP models continue to be vulnerable to bias. This bias often originates from the uneven distribution of real-world data and can propagate through the annotation process. Escalated integration of these models in…
Active learning theories and methods have been extensively studied in classical statistical learning settings. However, deep active learning, i.e., active learning with deep learning models, is usually based on empirical criteria without…