Proposes PA-DSL for correcting noisy human labels in automated data labeling.
problem Noisy human labels in automated data labeling.
method Uses adjudicated cases to correct noisy human labels and debias analyses.
result Maintains nominal coverage and reduces RMSE by 10-17% relative to using only adjudicated labels.
MCAL reduces labeling costs by 6x for auto-labeling data sets.
problem Expensive human annotation for ground-truth data sets.
method Iterative approach that trains a classifier to auto-label part of the data set, determining which samples to label using humans and which to label using the classifier at each step.
result 6x lower overall cost compared to human labeling the entire data set, always cheaper than competing strategies.
A method for collecting human supervision that combines rules and instance labels.
problem Lack of labeled data and inefficient human supervision.
method Rule-exemplar method with training algorithm for joint denoising and model training.
result Our algorithm is more accurate than existing methods and effectively denoises rules.
Unlike images or videos data which can be easily labeled by human being, sensor data annotation is a time-consuming process. However, traditional methods of human activity recognition require a large amount of such strictly labeled data for training classifiers. In this paper, we present an attention-based convolutiona…
This paper refines human labeling as a measurement process, revealing four sources of variation.
problem Systematic variation in human labeling obscures model learning.
method Introduces a statistical framework to decompose labeling outcomes.
result Empirical evidence for four components of labeling variation.
We propose Disentanglement based Active Learning (DAL), a new active learning technique based on self-supervision which leverages the concept of disentanglement. Instead of requesting labels from human oracle, our method automatically labels the majority of the datapoints, thus drastically reducing the human labeling b…
Majority Vote is optimal for reliable data labeling under certain conditions.
problem Reliable data labeling requires aggregating multiple annotators' labels, but the optimality of Majority Vote is not well understood.
method Characterized conditions under which Majority Vote achieves the optimal label estimation error.
result Majority Vote optimally recovers labels for a given class distribution under tolerable annotation noise limits.
The development of real-time affect detection models often depends upon obtaining annotated data for supervised learning by employing human experts to label the student data. One open question in annotating affective data for affect detection is whether the labelers (i.e., human experts) need to be socio-culturally sim…
Automates galaxy morphology classification with less human labelling.
problem Insufficient human-labeled galaxy images for accurate classification.
method Developed a VAE with equivariant transformer layers and a classifier network.
result Improves accuracy with fewer labels and unlabelled data.
Enhances AI models with human feedback for noisy data.
problem Improving AI model alignment with human feedback in noisy environments.
method Two-stage SL+LHF framework connecting machine learning with human feedback.
result The LNCA ratio identifies conditions for SL+LHF superiority over pure SL.
Generative Augmented Inference improves AI-generated data for causal inference.
problem Challenges in using AI-generated annotations for reliable causal inference.
method Generative Augmented Inference (GAI) treats AI outputs as informative features for learning true labels, flexibly modeling the relationship using nonparametric methods.
result GAI significantly reduces estimation error and improves confidence interval quality compared to human-only and PPI-based methods.
Generative models have made immense progress in recent years, particularly in their ability to generate high quality images. However, that quality has been difficult to evaluate rigorously, with evaluation dominated by heuristic approaches that do not correlate well with human judgment, such as the Inception Score and …
Paper tackles active learning under human label variation, proposing a new framework.
problem Active learning assumes a single ground truth, ignoring human label variation.
method Survey and propose a conceptual framework for HLV-aware active learning.
result Lay a conceptual foundation for HLV-aware active learning.
Study real-world noisy labels from human annotations for better understanding.
problem Understanding and modeling real-world label noise in machine learning.
method Developed two new benchmark datasets (CIFAR-10N, CIFAR-100N) with human-annotated real-world noisy labels.
result Real-world noisy labels exhibit instance-dependent patterns, not class-dependent as previously assumed.
LFD method improves text classification by making features clearer and less label-leaking.
problem Creating interpretable text representations that are both predictive and understandable.
method LFD method: proposes lexical and semantic features from contrastive text pairs, screens candidates using κ, and selects features by residual gain. result LFD features achieve higher human-human and human-LLM agreement than baseline concepts and are less label-leaking.
Humans are the final decision makers in critical tasks that involve ethical and legal concerns, ranging from recidivism prediction, to medical diagnosis, to fighting against fake news. Although machine learning models can sometimes achieve impressive performance in these tasks, these tasks are not amenable to full auto…
Relation extraction aims to extract relational facts from sentences. Previous models mainly rely on manually labeled datasets, seed instances or human-crafted patterns, and distant supervision. However, the human annotation is expensive, while human-crafted patterns suffer from semantic drift and distant supervision sa…
Human trafficking is among the most challenging law enforcement problems which demands persistent fight against from all over the globe. In this study, we leverage readily available data from the website "Backpage"-- used for classified advertisement-- to discern potential patterns of human trafficking activities which…
New method pools labels from similar data items to improve learning from small samples.
problem Learning from small, human-annotated samples with potential disagreement among annotators.
method Proposes neighborhood-based pooling for sharing labels across similar data items.
result Improves learning from small, noisy samples by pooling labels from similar items.
Paper proposes an alternative to anchor points for learning with noisy labels.
problem Learning with noisy labels is challenging due to inaccurate labels.
method Estimates transition matrix using clusterability condition and noisy labels.
result Estimation of transition matrix is more accurate and efficient than anchor points.
The paper studies how to allocate human validation in AI-assisted tasks to minimize errors.
problem Heterogeneous reliability of AI-generated signals across tasks, products, and customer segments.
method Tuned prediction-powered inference, upper confidence bounds policy, Neyman square-root rule.
result The proposed policy outperforms uniform and epsilon-greedy allocation, closing most of the gap to the oracle when reliability is heterogeneous.
In this work, we introduce a novel framework that employs cluster annotation to boost active learning by reducing the number of human interactions required to train deep neural networks. Instead of annotating single samples individually, humans can also label clusters, producing a higher number of annotated samples wit…
RAN model recognizes multiple activities from unlabeled sensor data.
problem Handling weakly labeled multi-activity data from wearable sensors.
method Recurrent Attention Networks (RAN) for sequential multi-activity recognition and localization.
result RAN model can infer multiple activities and determine activity locations from unlabeled data.
Plud system reduces labeling time and produces accurate models for uncategorized images.
problem Time-consuming manual labeling of uncategorized images.
method Iterative semi-supervised workflow combining clustering and classification.
result Reduces labeling time and produces accurate models.
Human analysts that use anomaly detection systems in practice want to retain the use of simple and explainable global anomaly detectors. In this paper, we propose a novel human-in-the-loop learning algorithm called GLAD (GLocalized Anomaly Detection) that supports global anomaly detectors. GLAD automatically learns the…
TIMELY improves consistency in labeling blood cell images.
problem Inconsistent labeling of blood cells in microscopy images leads to unreliable diagnoses.
method TIMELY combines pseudotime inference and hidden Markov trees to correct labeling mistakes.
result TIMELY outperforms baseline methods in identifying and correcting inconsistent labels.
Bayesian algorithms improve crowdsourcing with label and instance constraints.
problem Efficiently labeling large datasets with additional human annotator information.
method Developed Bayesian algorithms for semi-supervised crowdsourced classification under label and instance constraints.
result Improved performance compared to unsupervised crowdsourcing on various datasets.
Preventing early progression of epilepsy and so the severity of seizures requires an effective diagnosis. Epileptic transients indicate the ability to develop seizures but humans overlook such brief events in an electroencephalogram (EEG) what compromises patient treatment. Traditionally, training of the EEG event dete…
New research shows label refinement and weak training have limitations for aligning LLMs.
problem Limitations of refinement methods for aligning large language models.
method Analyzed probabilistic assumptions and alternative approaches to label refinement and weak training.
result Label refinement and weak training suffer from irreducible error, leaving a performance gap.
Develops methods to correct bias in AI feedback for more accurate alignment.
problem Systematic bias in AI feedback compared to human labels.
method Two debiased alignment methods: DDPO and DIPO.
result Methods improve alignment efficiency and performance close to human-labeled data.
For machine learning perception problems, human-level classification performance is used as an estimate of top algorithm performance. Thus, it is important to understand as precisely as possible the factors that impact human-level performance. Knowing this 1) provides a benchmark for model performance, 2) tells a proje…
Human labeling of data can be very time-consuming and expensive, yet, in many cases it is critical for the success of the learning process. In order to minimize human labeling efforts, we propose a novel active learning solution that does not rely on existing sources of unlabeled data. It uses a small amount of labeled…
Standard myopic active learning assumes that human annotations are always obtainable whenever new samples are selected. This, however, is unrealistic in many real-world applications where human experts are not readily available at all times. In this paper, we consider the single shot setting: all the required samples s…
CPATTA uses conformal prediction for efficient test-time adaptation.
problem Low data selection efficiency in existing ATTA methods.
method Conformal Prediction, online weight-update algorithm, domain-shift detector, staged update scheme.
result CPATTA consistently outperforms state-of-the-art methods by 5% in accuracy.
Bal-PM reduces preference labeling costs for LLMs.
problem Efficiently acquiring human feedback for preference modeling in large language models.
method Bayesian Active Learning with entropy maximization in feature space.
result Bal-PM reduces the number of required preference labels by 33% to 68%.
New benchmark for causal reasoning from human video descriptions.
problem Lack of diversity in event types and natural language descriptions, and differences from human judgments.
method Iterative event cloze task and data augmentation techniques.
result Improved data collection efficiency and diverse causal judgments.
Bayesian framework evaluates predictors of subjective visual tasks.
problem Evaluating uncertainty in machine learning predictors for tasks with subjective annotations.
method Bayesian framework to estimate epistemic uncertainty from human labels.
result Framework successfully applied to four image classification tasks.
MTL method uses unlabeled data with pseudo labels to improve classification with disjoint datasets.
problem Improving classification performance with disjoint labeled datasets using unlabeled data.
method Proposes MTL-SA method to select and augment unlabeled data with confident pseudo labels and close distribution to labeled data.
result Extensive experiments show the effectiveness of MTL-SA method in improving classification performance.
Humans take advantage of real world symmetries for various tasks, yet capturing their superb symmetry perception mechanism with a computational model remains elusive. Motivated by a new study demonstrating the extremely high inter-person accuracy of human perceived symmetries in the wild, we have constructed the first …
TBAL reduces manual annotation but requires validated data.
problem Creating large, high-quality labeled datasets.
method Threshold-based auto-labeling using human validation data.
result Sample complexity bounds on validation data needed.
Reward learning enables the application of reinforcement learning (RL) to tasks where reward is defined by human judgment, building a model of reward by asking humans questions. Most work on reward learning has used simulated environments, but complex information about values is often expressed in natural language, and…
Efficiently evaluate generative models at the prompt level using tensor factorization.
problem Fine-grained evaluations of generative models are costly and often misaligned with human judgment.
method Tensor factorization model that merges cheap autorater data with a small set of human gold-standard labels.
result The method provides accurate and tight confidence intervals for model performance.
We investigate active learning with access to two distinct oracles: Label (which is standard) and Search (which is not). The Search oracle models the situation where a human searches a database to seed or counterexample an existing solution. Search is stronger than Label while being natural to implement in many situati…
Paper tackles instance-dependent label noise by approximating it with part-dependent noise.
problem Learning with instance-dependent label noise is challenging.
method Approximate instance-dependent label noise with part-dependent noise. Use transition matrices for parts to model noise.
result Method outperforms state-of-the-art approaches for instance-dependent label noise.
New method labels GAN-generated faces without stereotyping.
problem Eliminating human bias in AI classification of fictional faces.
method Penalized regression to minimize cost function between realistic and target images.
result Successfully labels GAN-generated images without stereotyping.
IDS improves RLHF by smoothing reward data, enhancing model performance.
problem Reward model performance degrades and overoptimization hinders true objective.
method Iterative Data Smoothing (IDS) updates model and data labels during each epoch.
result IDS outperforms traditional methods in RLHF.
Lack of labeled training data is a major bottleneck for neural network based aspect and opinion term extraction on product reviews. To alleviate this problem, we first propose an algorithm to automatically mine extraction rules from existing training examples based on dependency parsing results. The mined rules are the…
Optimizes AI learning with limited human feedback budgets.
problem Optimizing allocation of a fixed annotation budget for AI learning.
method Preference-Calibrated Active Learning (PCAL) using semi-parametric inference.
result Proves asymptotic optimality and robustness of the PCAL estimator.