Yi Cai

According to our database, Yi Cai authored at least 9 papers between 2021 and 2026.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2026

Rethinking Explanation Evaluation Under the Retraining Scheme.

Yi Cai, Thibaud Ardoin, Mayank Gulati, Gerhard Wunder

Proceedings of the Fortieth AAAI Conference on Artificial Intelligence, 2026

2025

GEFA: A General Feature Attribution Framework Using Proxy Gradient Estimation.

Yi Cai, Thibaud Ardoin, Gerhard Wunder

Proceedings of the Forty-second International Conference on Machine Learning, 2025

Where Confabulation Lives: Latent Feature Discovery in LLMs.

Thibaud Ardoin, Yi Cai, Gerhard Wunder

Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025

2024

Transparent Neighborhood Approximation for Text Classifier Explanation.

Yi Cai, Arthur Zimek, Eirini Ntoutsi, Gerhard Wunder

CoRR, 2024

On Gradient-like Explanation under a Black-box Setting: When Black-box Explanations Become as Good as White-box.

Yi Cai, Gerhard Wunder

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Transparent Neighborhood Approximation for Text Classifier Explanation by Probability-Based Editing.

Yi Cai, Arthur Zimek, Eirini Ntoutsi, Gerhard Wunder

Proceedings of the 11th IEEE International Conference on Data Science and Advanced Analytics, 2024

2023

Explaining text classifiers through progressive neighborhood approximation with realistic samples.

Yi Cai, Arthur Zimek, Eirini Ntoutsi, Gerhard Wunder

CoRR, 2023

2022

Power of Explanations: Towards automatic debiasing in hate speech detection.

Yi Cai, Arthur Zimek, Gerhard Wunder, Eirini Ntoutsi

Proceedings of the 9th IEEE International Conference on Data Science and Advanced Analytics, 2022

2021

XPROAX-Local explanations for text classification with progressive neighborhood approximation.

Yi Cai, Arthur Zimek, Eirini Ntoutsi

Proceedings of the 8th IEEE International Conference on Data Science and Advanced Analytics, 2021