With the rapid growth of crowdsourcing platforms it has become easy and relatively inexpensive to collect a dataset labeled by multiple annotators in a short time. However due to the lack of control over the quality of the annotators, some abnormal annotators may be affected by position bias which can potentially degra…
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
169,051 papers · 148 categories
Trend · papers per month
48 results for “Controlled Annotations”
Generative AI reduces IR evaluation costs but introduces errors; this work provides reliable CIs.
problem Generating relevance annotations using AI introduces errors that affect IR evaluation metrics.
method Proposes two methods: prediction-powered inference and conformal risk control to place reliable CIs around IR metrics.
result Proposed methods accurately capture both variance and bias in evaluation based on AI-generated annotations.
A simple method reduces bias in LLM auto-evaluators by controlling output length.
problem Bias in LLM auto-annotators, particularly length bias.
method Simple regression analysis to control for length difference and other mediators.
result Improved robustness and increased correlation with human preferences.
Paper introduces a new pedestrian dataset for adverse weather conditions.
problem Lack of controlled and annotated pedestrian datasets for adverse weather conditions.
method Presentation of a new dataset and baseline results for various machine learning tasks.
result Baseline results for various tasks on the Cerema AWP dataset.
Interactive IL beats BC by state-wise annotation cost.
problem Behavior Cloning struggles with annotation cost in sequential decision making.
method Proved Stagger and Warm Stagger algorithms to outperform BC.
result Interactive and hybrid IL methods outperform BC with state-wise annotation.
A method to generate multi-label data from single positive annotations.
problem Generating multi-label datasets is costly and impractical.
method Single-to-multi-label (S2M) sampling using Markov chain Monte Carlo.
result S2M sampling enables high-quality multi-label data with minimal annotation cost.
A survey of existing methods for stopping active learning (AL) reveals the needs for methods that are: more widely applicable; more aggressive in saving annotations; and more stable across changing datasets. A new method for stopping AL based on stabilizing predictions is presented that addresses these needs. Furthermo…
The paper proposes a method to learn from neighbor annotations to improve predictions in ambiguous tasks.
problem Ambiguity in structured prediction problems with large output spaces makes exhaustive annotation impractical.
method Proposes an objective to transfer supervision from neighboring examples to improve predictions.
result Consistent improvements over standard maximum likelihood training and baselines in multi-label classification and image-grounded sequence modeling tasks.
Study compares methods for detecting novelty in textual data streams.
problem Lack of annotated datasets for novelty detection.
method Simulation framework to create controlled datasets and benchmark methods.
result Evaluation of state-of-the-art methods on different types of novelty.
Generative model tackles inconsistent attributes across datasets by enabling precise conditional generation.
problem Inconsistent attributes across merged datasets limit controllability in conditional generative modeling.
method Diffusion Model with Double Guidance, maintaining control over multiple conditions without joint annotations.
result Outperforms baselines in molecular and image generation tasks, aligning with target distributions and controlling missing conditions.
Integrating Crowdsourcing and Active Learning for Classification of Work-Life Events from Tweetscs.CL
Crowdsourcing and active learning reduce manual annotation in social media event classification.
problem Manual annotation is time-consuming and resource-intensive in social media event classification.
method Crowdsourcing pipeline combined with active learning strategies.
result Active learning strategies help reduce the number of tweets needed for classification.
Study shows partially-typed NER datasets can match fully-typed ones in model performance.
problem Leveraging multiple partially-typed NER datasets for training models without fully-typed annotations.
method Systematic analysis and controlled experiments comparing partially-typed and fully-typed datasets.
result Models trained with partially-typed annotations can achieve similar performance to those trained with fully-typed annotations.
Framework uses human annotations to make models robust to spurious correlations.
problem Machine learning models fail when unmeasured variables change test distributions.
method Human annotations to augment training examples, UV-DRO objective for robustness.
result Improvements of 5-10% on digit recognition task and 1.5-5% on NYPD Police Stops analysis.
Generic generation and manipulation of text is challenging and has limited success compared to recent deep generative modeling in visual domain. This paper aims at generating plausible natural language sentences, whose attributes are dynamically controlled by learning disentangled latent representations with designated…
New method uses imperfect LLM annotations for valid statistical inference in social science.
problem Inaccurate large language model annotations in social science research.
method Design-based supervised learning (DSL) combining imperfect LLM surrogates with gold-standard labels.
result DSL provides valid statistical inference with comparable predictive accuracy to existing methods.
LLMs struggle with zero-shot annotation tasks due to model-internalized priors.
problem Impact of model-internalized priors on LLM performance in zero-shot annotation tasks.
method Investigated three dimensions: familiarity, decision stickiness, and susceptibility to misaligned task definitions.
result Nearly two-thirds of zero-shot errors are resistant to correction, with a rescue rate of 34.8%. Definition-Specific Familiarity (DSF) shows a positive association with model performance.
Learning-based methods for visual segmentation have made progress on particular types of segmentation tasks, but are limited by the necessary supervision, the narrow definitions of fixed tasks, and the lack of control during inference for correcting errors. To remedy the rigidity and annotation burden of standard appro…
Study shows annotation instrument design affects model performance in hate speech detection.
problem Impact of annotation instrument design on model performance in hate speech detection.
method Collected annotations from five experimental conditions of an annotation instrument, fine-tuned BERT models on each dataset, evaluated performance on holdout portion.
result Significant differences in model performance and annotations across conditions.
Clearing algorithm improves CT image segmentation accuracy by merging confident annotations.
problem Inaccurate predictions due to noisy annotations from different annotators.
method 3-stage algorithm: scoring annotators, scoring nodules, merging annotations.
result Improves prediction accuracy in CT image segmentation tasks.
The paper proposes methods to control errors in language generation models using textual entailment.
problem The lack of a correctness metric hinders applying principled methods to language generation tasks.
method The paper leverages textual entailment to evaluate correctness and proposes two selective generation algorithms: SGen^Sup and SGen^Semi.
result The proposed algorithms control the false discovery rate with respect to textual entailment and achieve comparable selection efficiency to baselines.
New method to estimate doctors' effort in annotating medical images.
problem High effort and expense in annotating medical images.
method Proposes a new criterion to evaluate effort, uses active learning and U-shape network for annotation strategy, and fine annotation platform to reduce effort.
result State-of-the-art segmentation performance achieved with only 60% annotation candidates, reducing effort by 44-47%.
Active learning selects both observations and annotation precision for Gaussian Processes.
problem Costly annotation in supervised learning.
method Proposes an active learning algorithm that selects observations and annotation precision, using a modified BALD objective.
result Empirically shows the benefits of adjusting annotation precision in active learning.
Generative model combines multi-dimensional annotations for more accurate ground truth estimation.
problem Inaccurate ground truth estimation from naive annotators' multi-dimensional annotations.
method Proposes a joint multi-dimensional model for global and time-series annotation fusion using Expectation-Maximization algorithm.
result More accurate ground truth estimates through joint modeling of multiple dimensions.
Survey on AL strategies for cost-effective annotation in classification.
problem Real-world AL challenges due to human annotators' limitations.
method Categorizes 60 real-world AL strategies considering multiple annotators, query types, and cost schemes.
result General real-world AL strategy introduced for categorization of 60 strategies.
Robustness to Subpopulation Shift with Domain Label Noise via Regularized Annotation of Domainscs.LG
RAD improves robustness to domain annotation noise without explicit domain annotations.
problem Robustness to domain annotation noise in training data.
method Regularized Annotation of Domains (RAD) for last layer retraining.
result RAD outperforms state-of-the-art methods even with 5% noise in training data.
The study challenges the notion that partial data annotation is inferior, suggesting it can sometimes outperform complete annotation.
problem The inefficiency and high cost of completely annotating structured data.
method Information theoretic formulation applied to three diverse structured learning tasks.
result Learning from partial structures can sometimes outperform learning from complete ones.
A new method uses triplet embeddings to improve human annotation for hidden constructs.
problem Improving human annotation for hidden constructs in machine learning.
method Proposes a novel annotation approach using triplet embeddings to lift absolute annotations to relative comparisons.
result Successfully represents synthetic hidden constructs in time under noisy sampling conditions.
PTBCC improves accuracy in multi-class annotation aggregation by learning from prototype confusion matrices.
problem Inaccurate and insufficient confusion matrices for annotators in multi-class classification tasks.
method PTBCC (ProtoType learning-driven Bayesian Classifier Combination) uses prototype confusion matrices to capture annotator expertise.
result PTBCC achieves up to 15% accuracy improvement and 3% higher average accuracy compared to existing methods.
ActiveLab improves classifier accuracy with fewer annotations by re-labeling.
problem Imperfect labels from multiple annotators in real-world data.
method ActiveLab automatically decides when to re-label examples for better classifier training.
result ActiveLab trains more accurate classifiers with fewer annotations.
Bayesian methods improve text annotation quality.
problem Inconsistent and unreliable human annotations in natural language processing.
method Two semi-supervised Bayesian methods: a deep learning model and an ensemble method.
result Bayesian methods enhance the reliability and performance of BERT models.
The Impact of Annotation Guidelines and Annotated Data on Extracting App Features from App Reviewscs.IR
Study improves app feature extraction models with new annotation guidelines and data.
problem Improving the quality and usefulness of app feature extraction models.
method Exploring the effects of annotation guidelines and annotated data on app feature extraction models.
result New annotation guidelines lead to less noisy and more informative app features.
Paper proposes an efficient method for bounding box annotation in object detection.
problem Manual annotation of bounding boxes is tedious and resource-intensive.
method Iterative training of object detector on small batches of labeled images, with human annotator correcting errors.
result Significant reduction in human annotation effort, up to 75%.
Paper explores unsupervised learning for speech synthesis control.
problem Learning control over speech output without labeled data.
method Study of unsupervised training heuristics and autoencoder models.
result Unsupervised methods can be interpreted as variational inference.
Paper proposes a weak supervision technique for CNN semantic segmentation of lung diseases using partially annotated data.
problem Creating annotated datasets for semantic segmentation of lung diseases is laborious and time-consuming.
method Proposes a weak supervision technique that utilizes partially annotated datasets to improve CNN semantic segmentation accuracy.
result Significantly improved segmentation accuracy using partially annotated datasets.
Neural network improves aneurysm classification accuracy in MRI images.
problem Classifying aneurysm status in MRI images with varying radiologist expertise.
method Constructed neural network trained on radiologists' annotations, compared to a control model.
result Proposed model had a higher area under the curve (0.845 vs. 0.793).
Paper proposes a method for faster object detection annotation in indoor scenes.
problem Efficiently annotate object detection datasets in indoor scenes.
method Two-stage annotation process: manual annotation of a part of the dataset, followed by automatic annotation of the rest.
result The two-stage method significantly reduces the total workload compared to manual annotation of the entire dataset.
A new method for faster data annotation using click-supervision and hierarchical object detection.
problem Data annotation bottleneck in modern data collection.
method Semi-automatic approach combining human and neural network for hierarchical object detection.
result Improved annotation speed and accuracy compared to current methods.
Improves off-policy evaluation with imperfect annotations.
problem Limited dataset coverage for evaluating new policies.
method Doubly robust estimators combining IS and DM, incorporating counterfactual annotations.
result Using annotations within the DM component yields the most desirable theoretical results.
A popular approach for large scale data annotation tasks is crowdsourcing, wherein each data point is labeled by multiple noisy annotators. We consider the problem of inferring ground truth from noisy ordinal labels obtained from multiple annotators of varying and unknown expertise levels. Annotation models for ordinal…
A distributed approach for efficient metric learning.
problem Efficiently learning metrics for large datasets.
method Discriminative metric learning on subsets, then aggregating results.
result ADML achieves state-of-the-art performance at lower computational cost.
Crowdlab uses classifiers to estimate consensus labels and annotator quality.
problem Leveraging multiple annotators for data classification.
method Weighted ensemble approach using any trained classifier.
result Superior estimates for consensus labels and annotator quality.
Method learns true labels from noisy annotators using regularization.
problem Learning from noisy labels in supervised learning.
method Regularized estimation of annotator confusion matrices.
result Method outperforms state-of-the-art methods in image classification.
Cluster annotation reduces active learning human interactions.
problem Reducing human interactions in active learning.
method Cluster annotation to label multiple samples at once.
result 82% and 87% less human interactions for CIFAR-10 and EuroSAT datasets.
Leveraging Crowdsourcing Data For Deep Active Learning - An Application: Learning Intents in Alexacs.LG
This paper presents a generic Bayesian framework that enables any deep learning model to actively learn from targeted crowds. Our framework inherits from recent advances in Bayesian deep learning, and extends existing work by considering the targeted crowdsourcing approach, where multiple annotators with unknown expert…
New method uses artificial data to improve biomedical text tagging.
problem Lack of labeled data for biomedical tasks.
method Fine-tuning a pre-trained encoder with additional artificial labeled instances.
result Achieved state-of-the-art performance in PICO annotation.
The paper proposes incentivizing human annotators with 'golden questions' to improve data quality.
problem Ensuring high-quality human annotations for training large language models.
method A principal-agent model is used to incentivize annotators with bonuses based on the maximum likelihood estimators (MLE) of their annotations. Hypothesis testing is applied to monitor the annotators' performance.
result The hypothesis testing rate for the principal-agent model is of , highlighting the importance of 'golden questions' for monitoring annotators.
Paper proposes active learning for sound event detection with reduced annotation effort.
problem Reducing annotation effort for sound event detection.
method Change point detection for candidate selection, mismatch-first farthest-traversal for selection, training with context recordings.
result The proposed system achieves similar performance to full annotation with only 2% of data, reducing annotation effort.
Paper proposes a method to reduce annotation time for 3D object detection.
problem Effort and time required for generating 3D object annotations.
method Combines human supervision with pretrained neural networks for 3D point cloud segmentation and bounding box generation.
result Reduces human annotation time by 30x.