Search Results for author:
Found 22 papers, 4 papers with code
Foundation Models at Work: Fine-Tuning for Fairness in Algorithmic Hiring
The experiments on a public hiring dataset and a real-world hiring platform showcase how large language models can assist in identifying and mitigation biases in the real world.
Making Bias Amplification in Balanced Datasets Directional and Interpretable
However, these metrics fail to measure biases when A is balanced with T. To measure bias amplification in balanced datasets, recent work proposed a predictability-based metric called leakage amplification.
Classification Drives Geographic Bias in Street Scene Segmentation
While earlier work studied general-purpose image datasets (e. g., ImageNet) and simple tasks like image recognition, we investigated geo-biases in real-world driving datasets on a more complex task: instance segmentation.
Black-box Uncertainty Quantification Method for LLM-as-a-Judge
In this paper, we introduce a novel method for quantifying uncertainty designed to enhance the trustworthiness of LLM-as-a-Judge evaluations.
On Efficient and Statistical Quality Estimation for Data Annotation
Basing estimates on small sample sizes, however, can lead to imprecise values for the error rate.
Ranking Large Language Models without Ground Truth
and a set of LLMs, we rank them without access to any ground truth or reference responses.
Explaining Knock-on Effects of Bias Mitigation
In this paper, we aim to characterise impacted cohorts when mitigation interventions are applied.
Iterative Reward Shaping using Human Feedback for Correcting Reward Misspecification
Our approach allows the user to provide trajectory-level feedback on agent's behavior during training, which can be integrated as a reward shaping signal in the following training iteration.
Co-creating a globally interpretable model with human input
We consider an aggregated human-AI collaboration aimed at generating a joint interpretable model.
Interpretable Differencing of Machine Learning Models
Understanding the differences between machine learning (ML) models is of interest in scenarios ranging from choosing amongst a set of competing models, to updating a deployed model with new training data.
AutoDOViz: Human-Centered Automation for Decision Optimization
AutoDOViz seeks to lower the barrier of entry for data scientists in problem specification for reinforcement learning problems, leverage the benefits of AutoDO algorithms for RL pipeline search and finally, create visualizations and policy insights in order to facilitate the typical interactive nature when communicating problem formulation and solution proposals between DO experts and domain experts.
On the Safety of Interpretable Machine Learning: A Maximum Deviation Approach
Interpretable and explainable machine learning has seen a recent surge of interest.
Boolean Decision Rules for Reinforcement Learning Policy Summarisation
Explainability of Reinforcement Learning (RL) policies remains a challenging research problem, particularly when considering RL in a safety context.
User Driven Model Adjustment via Boolean Rule Explanations
AI solutions are heavily dependant on the quality and accuracy of the input training data, however the training data may not always fully reflect the most up-to-date policy landscape or may be missing business logic.
FROTE: Feedback Rule-Driven Oversampling for Editing Models
However, in such scenarios, it may take time for sufficient training data to accumulate in order to retrain the model to reflect the new decision boundaries.
Contrastive Explanations for Comparing Preferences of Reinforcement Learning Agents
In complex tasks where the reward function is not straightforward and consists of a set of objectives, multiple reinforcement learning (RL) policies that perform task adequately, but employ different strategies can be trained by adjusting the impact of individual objectives on reward function.
Neo: Generalizing Confusion Matrix Visualization to Hierarchical and Multi-Output Labels
The confusion matrix, a ubiquitous visualization for helping people evaluate machine learning models, is a tabular layout that compares predicted class labels against actual class labels over all data instances.
Perfusion Quantification from Endoscopic Videos: Learning to Read Tumor Signatures
Intra-operative identification of malignant versus benign or healthy tissue is a major challenge in fluorescence guided cancer surgery.
Towards Automated Extraction of Business Constraints from Unstructured Regulatory Text
Large organizations spend considerable resources in reviewing regulations and ensuring that their business processes are compliant with the law.
Learning the Correction for Multi-Path Deviations in Time-of-Flight Cameras
Secondly, we used this dataset to construct a learning model to predict real valued corrections to the ToF data using Random Forests.
Reflection Modeling for Passive Stereo
Stereo reconstruction in presence of reality faces many challenges that still need to be addressed.
Ensemble Learning for Confidence Measures in Stereo Vision
With the aim to improve accuracy of stereo confidence measures, we apply the random decision forest framework to a large set of diverse stereo confidence measures.
