Search | OpenScholar

Search results

7 results found

Are Your Explanations Reliable? Investigating the Stability of LIME in Explaining Text Classifiers by Marrying XAI and Adversarial Attack

Publication: Journal Article

Burger, Christopher, Lingwei Chen, and Thai Le. 2023. “Are Your Explanations Reliable? Investigating the Stability of LIME in Explaining Text Classifiers by Marrying XAI and Adversarial Attack”. Empirical Methods in Natural Language Processing.

Improving Robustness Estimates in Natural Language Explainable AI though Synonymity Weighted Similarity Measures

Publication: Working Paper

Burger, Christopher. In Preparation. “Improving Robustness Estimates in Natural Language Explainable AI Though Synonymity Weighted Similarity Measures.”

Beyond Individual Facts: Investigating Categorical Knowledge Locality of Taxonomy and Meronomy Concepts in GPT Models

Publication: Working Paper

Burger, Christopher, Yifan Hu, and Thai Le. In Preparation. “Beyond Individual Facts: Investigating Categorical Knowledge Locality of Taxonomy and Meronomy Concepts in GPT Models.”

Towards Robust and Accurate Stability Estimation of Local Surrogate Models in Text-based Explainable AI

Publication: Working Paper

Burger, Christopher, Charles Walter, Thai Le, and Lingwei Chen. In Preparation. “Towards Robust and Accurate Stability Estimation of Local Surrogate Models in Text-Based Explainable AI.”

Improving Stability Estimates in Adversarial Explainable AI through Alternate Search Methods

Publication: Journal Article

Burger, Christopher, and Charles Walter. 2025. “Improving Stability Estimates in Adversarial Explainable AI through Alternate Search Methods”. Proceedings of the 58th Hawaii International Conference on System Sciences.

The Effect of Similarity Measures on Accurate Stability Estimates for Local Surrogate Models in Text-based Explainable AI

Publication: Working Paper

Burger, Christopher, Charles Walter, and Thai Le. In Preparation. “The Effect of Similarity Measures on Accurate Stability Estimates for Local Surrogate Models in Text-Based Explainable AI.”

cburger