Picture for Muhammad Bilal Zafar

Muhammad Bilal Zafar

MPI-SWS

When Should We Orchestrate Multiple Agents?

Add code
Mar 17, 2025
Viaarxiv icon

Can LLMs Explain Themselves Counterfactually?

Add code
Feb 25, 2025
Viaarxiv icon

The Impact of Inference Acceleration Strategies on Bias of LLMs

Add code
Oct 29, 2024
Viaarxiv icon

Evaluating Large Language Models with fmeval

Add code
Jul 15, 2024
Figure 1 for Evaluating Large Language Models with fmeval
Figure 2 for Evaluating Large Language Models with fmeval
Figure 3 for Evaluating Large Language Models with fmeval
Figure 4 for Evaluating Large Language Models with fmeval
Viaarxiv icon

On Early Detection of Hallucinations in Factual Question Answering

Add code
Dec 27, 2023
Viaarxiv icon

Efficient fair PCA for fair representation learning

Add code
Feb 26, 2023
Viaarxiv icon

What You Like: Generating Explainable Topical Recommendations for Twitter Using Social Annotations

Add code
Dec 23, 2022
Figure 1 for What You Like: Generating Explainable Topical Recommendations for Twitter Using Social Annotations
Figure 2 for What You Like: Generating Explainable Topical Recommendations for Twitter Using Social Annotations
Figure 3 for What You Like: Generating Explainable Topical Recommendations for Twitter Using Social Annotations
Figure 4 for What You Like: Generating Explainable Topical Recommendations for Twitter Using Social Annotations
Viaarxiv icon

Diverse Counterfactual Explanations for Anomaly Detection in Time Series

Add code
Mar 21, 2022
Figure 1 for Diverse Counterfactual Explanations for Anomaly Detection in Time Series
Figure 2 for Diverse Counterfactual Explanations for Anomaly Detection in Time Series
Figure 3 for Diverse Counterfactual Explanations for Anomaly Detection in Time Series
Figure 4 for Diverse Counterfactual Explanations for Anomaly Detection in Time Series
Viaarxiv icon

More Than Words: Towards Better Quality Interpretations of Text Classifiers

Add code
Dec 23, 2021
Figure 1 for More Than Words: Towards Better Quality Interpretations of Text Classifiers
Figure 2 for More Than Words: Towards Better Quality Interpretations of Text Classifiers
Figure 3 for More Than Words: Towards Better Quality Interpretations of Text Classifiers
Figure 4 for More Than Words: Towards Better Quality Interpretations of Text Classifiers
Viaarxiv icon

Amazon SageMaker Model Monitor: A System for Real-Time Insights into Deployed Machine Learning Models

Add code
Dec 13, 2021
Figure 1 for Amazon SageMaker Model Monitor: A System for Real-Time Insights into Deployed Machine Learning Models
Figure 2 for Amazon SageMaker Model Monitor: A System for Real-Time Insights into Deployed Machine Learning Models
Figure 3 for Amazon SageMaker Model Monitor: A System for Real-Time Insights into Deployed Machine Learning Models
Figure 4 for Amazon SageMaker Model Monitor: A System for Real-Time Insights into Deployed Machine Learning Models
Viaarxiv icon