Picture for Mateusz Lango

Mateusz Lango

OpeNLGauge: An Explainable Metric for NLG Evaluation with Open-Weights LLMs

Add code
Mar 14, 2025
Viaarxiv icon

Leveraging Large Language Models for Building Interpretable Rule-Based Data-to-Text Systems

Add code
Feb 28, 2025
Viaarxiv icon

Polish-ASTE: Aspect-Sentiment Triplet Extraction Datasets for Polish

Add code
Feb 27, 2025
Viaarxiv icon

Counterfactual Explanations with Probabilistic Guarantees on their Robustness to Model Change

Add code
Aug 09, 2024
Viaarxiv icon

Faithful and Plausible Natural Language Explanations for Image Classification: A Pipeline Approach

Add code
Jul 30, 2024
Figure 1 for Faithful and Plausible Natural Language Explanations for Image Classification: A Pipeline Approach
Figure 2 for Faithful and Plausible Natural Language Explanations for Image Classification: A Pipeline Approach
Figure 3 for Faithful and Plausible Natural Language Explanations for Image Classification: A Pipeline Approach
Figure 4 for Faithful and Plausible Natural Language Explanations for Image Classification: A Pipeline Approach
Viaarxiv icon

A Survey of Text Style Transfer: Applications and Ethical Implications

Add code
Jul 23, 2024
Viaarxiv icon

Generating clickbait spoilers with an ensemble of large language models

Add code
May 25, 2024
Viaarxiv icon

Multi-criteria approach for selecting an explanation from the set of counterfactuals produced by an ensemble of explainers

Add code
Mar 20, 2024
Viaarxiv icon

Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMs

Add code
Feb 06, 2024
Figure 1 for Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMs
Figure 2 for Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMs
Figure 3 for Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMs
Figure 4 for Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMs
Viaarxiv icon

The Problem of Coherence in Natural Language Explanations of Recommendations

Add code
Dec 18, 2023
Viaarxiv icon