Related papers: Beyond Labels: Information-Efficient Human-in-the-…
Recent advancements in \textit{Learning from Human Feedback} present an effective way to train robot agents via inputs from non-expert humans, without a need for a specially designed reward function. However, this approach needs a human to…
Traditional data mining algorithms are exceptional at seeing patterns in data that humans cannot, but are often confused by details that are obvious to the organic eye. Algorithms that include humans "in-the-loop" have proved beneficial for…
The large size and complex decision mechanisms of state-of-the-art text classifiers make it difficult for humans to understand their predictions, leading to a potential lack of trust by the users. These issues have led to the adoption of…
Recent studies highlight that deep learning models often learn spurious features mistakenly linked to labels, compromising their reliability in real-world scenarios where such correlations do not hold. Despite the increasing research…
Assessing the degree of semantic relatedness between words is an important task with a variety of semantic applications, such as ontology learning for the Semantic Web, semantic search or query expansion. To accomplish this in an automated…
Data annotated by humans is a source of knowledge by describing the peculiarities of the problem and therefore fueling the decision process of the trained model. Unfortunately, the annotation process for subjective natural language…
Machine learning techniques applied to the Natural Language Processing (NLP) component of conversational agent development show promising results for improved accuracy and quality of feedback that a conversational agent can provide. The…
This paper proposes a novel training scheme for fast matching models in Search Ads, which is motivated by the real challenges in model training. The first challenge stems from the pursuit of high throughput, which prohibits the deployment…
The unprecedented demand for large amount of data has catalyzed the trend of combining human insights with machine learning techniques, which facilitate the use of crowdsourcing to enlist label information both effectively and efficiently.…
We often desire our models to be interpretable as well as accurate. Prior work on optimizing models for interpretability has relied on easy-to-quantify proxies for interpretability, such as sparsity or the number of operations required. In…
Collecting high-quality labeled data for model training is notoriously time-consuming and labor-intensive for various NLP tasks. While copious solutions, such as active learning for small language models (SLMs) and prevalent in-context…
This paper introduces a novel crowdsourcing worker selection algorithm, enhancing annotation quality and reducing costs. Unlike previous studies targeting simpler tasks, this study contends with the complexities of label interdependencies…
We analyze a reversed-supervision strategy that searches over labelings of a large unlabeled set \(B\) to minimize error on a small labeled set \(A\). The search space is \(2^n\), and the resulting complexity remains exponential even under…
Given a (machine learning) classifier and a collection of unlabeled data, how can we efficiently identify misclassification patterns presented in this dataset? To address this problem, we propose a human-machine collaborative framework that…
Training of convolutional neural networks for semantic segmentation requires accurate pixel-wise labeling which requires large amounts of human effort. The human-in-the-loop method reduces labeling effort; however, it requires human…
This paper introduces a cost-efficient active learning (AL) framework for classification, featuring a novel query design called candidate set query. Unlike traditional AL queries requiring the oracle to examine all possible classes, our…
Active learning aims to identify the most informative data from an unlabeled data pool that enables a model to reach the desired accuracy rapidly. This benefits especially deep neural networks which generally require a huge number of…
System-provided explanations for recommendations are an important component towards transparent and trustworthy AI. In state-of-the-art research, this is a one-way signal, though, to improve user acceptance. In this paper, we turn the role…
In-context learning (ICL) enables large language models to perform new tasks by conditioning on a sequence of examples. Most prior work reasonably and intuitively assumes that which examples are chosen has a far greater effect on…
Active learning aims to reduce the high labeling cost involved in training machine learning models on large datasets by efficiently labeling only the most informative samples. Recently, deep active learning has shown success on various…