Picture for Muhammed Yusuf Kocyigit

Muhammed Yusuf Kocyigit

Evaluation data contamination in LLMs: how do we measure it and (when) does it matter?

Add code
Nov 06, 2024
Viaarxiv icon

On Measuring Social Biases in Prompt-Based Multi-Task Learning

Add code
May 23, 2022
Figure 1 for On Measuring Social Biases in Prompt-Based Multi-Task Learning
Figure 2 for On Measuring Social Biases in Prompt-Based Multi-Task Learning
Figure 3 for On Measuring Social Biases in Prompt-Based Multi-Task Learning
Figure 4 for On Measuring Social Biases in Prompt-Based Multi-Task Learning
Viaarxiv icon

Challenges in Measuring Bias via Open-Ended Language Generation

Add code
May 23, 2022
Figure 1 for Challenges in Measuring Bias via Open-Ended Language Generation
Figure 2 for Challenges in Measuring Bias via Open-Ended Language Generation
Figure 3 for Challenges in Measuring Bias via Open-Ended Language Generation
Figure 4 for Challenges in Measuring Bias via Open-Ended Language Generation
Viaarxiv icon

Better Quality Estimation for Low Resource Corpus Mining

Add code
Mar 15, 2022
Figure 1 for Better Quality Estimation for Low Resource Corpus Mining
Figure 2 for Better Quality Estimation for Low Resource Corpus Mining
Figure 3 for Better Quality Estimation for Low Resource Corpus Mining
Figure 4 for Better Quality Estimation for Low Resource Corpus Mining
Viaarxiv icon

NUBIA: NeUral Based Interchangeability Assessor for Text Generation

Add code
May 01, 2020
Figure 1 for NUBIA: NeUral Based Interchangeability Assessor for Text Generation
Figure 2 for NUBIA: NeUral Based Interchangeability Assessor for Text Generation
Figure 3 for NUBIA: NeUral Based Interchangeability Assessor for Text Generation
Figure 4 for NUBIA: NeUral Based Interchangeability Assessor for Text Generation
Viaarxiv icon