Picture for Sameep Mehta

Sameep Mehta

xLP: Explainable Link Prediction for Master Data Management

Mar 14, 2024
Figure 1 for xLP: Explainable Link Prediction for Master Data Management
Figure 2 for xLP: Explainable Link Prediction for Master Data Management
Figure 3 for xLP: Explainable Link Prediction for Master Data Management
Figure 4 for xLP: Explainable Link Prediction for Master Data Management
Viaarxiv icon

LLMGuard: Guarding Against Unsafe LLM Behavior

Feb 27, 2024
Figure 1 for LLMGuard: Guarding Against Unsafe LLM Behavior
Figure 2 for LLMGuard: Guarding Against Unsafe LLM Behavior
Viaarxiv icon

"Beware of deception": Detecting Half-Truth and Debunking it through Controlled Claim Editing

Aug 15, 2023
Viaarxiv icon

CFL: Causally Fair Language Models Through Token-level Attribute Controlled Generation

Add code
Jun 01, 2023
Figure 1 for CFL: Causally Fair Language Models Through Token-level Attribute Controlled Generation
Figure 2 for CFL: Causally Fair Language Models Through Token-level Attribute Controlled Generation
Figure 3 for CFL: Causally Fair Language Models Through Token-level Attribute Controlled Generation
Figure 4 for CFL: Causally Fair Language Models Through Token-level Attribute Controlled Generation
Viaarxiv icon

Data Quality Toolkit: Automatic assessment of data quality and remediation for machine learning datasets

Sep 05, 2021
Figure 1 for Data Quality Toolkit: Automatic assessment of data quality and remediation for machine learning datasets
Figure 2 for Data Quality Toolkit: Automatic assessment of data quality and remediation for machine learning datasets
Figure 3 for Data Quality Toolkit: Automatic assessment of data quality and remediation for machine learning datasets
Figure 4 for Data Quality Toolkit: Automatic assessment of data quality and remediation for machine learning datasets
Viaarxiv icon

Explainable Link Prediction for Privacy-Preserving Contact Tracing

Dec 10, 2020
Figure 1 for Explainable Link Prediction for Privacy-Preserving Contact Tracing
Figure 2 for Explainable Link Prediction for Privacy-Preserving Contact Tracing
Figure 3 for Explainable Link Prediction for Privacy-Preserving Contact Tracing
Figure 4 for Explainable Link Prediction for Privacy-Preserving Contact Tracing
Viaarxiv icon

Data Readiness Report

Oct 15, 2020
Figure 1 for Data Readiness Report
Figure 2 for Data Readiness Report
Figure 3 for Data Readiness Report
Figure 4 for Data Readiness Report
Viaarxiv icon

Fair Transfer of Multiple Style Attributes in Text

Jan 18, 2020
Figure 1 for Fair Transfer of Multiple Style Attributes in Text
Figure 2 for Fair Transfer of Multiple Style Attributes in Text
Figure 3 for Fair Transfer of Multiple Style Attributes in Text
Figure 4 for Fair Transfer of Multiple Style Attributes in Text
Viaarxiv icon

Hardening Deep Neural Networks via Adversarial Model Cascades

Nov 04, 2018
Figure 1 for Hardening Deep Neural Networks via Adversarial Model Cascades
Figure 2 for Hardening Deep Neural Networks via Adversarial Model Cascades
Figure 3 for Hardening Deep Neural Networks via Adversarial Model Cascades
Figure 4 for Hardening Deep Neural Networks via Adversarial Model Cascades
Viaarxiv icon

AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Bias

Add code
Oct 03, 2018
Figure 1 for AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Bias
Figure 2 for AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Bias
Figure 3 for AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Bias
Figure 4 for AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Bias
Viaarxiv icon