Trust Me, I'm Wrong: High-Certainty Hallucinations in LLMs.
CoRR, February, 2025
Distinguishing Ignorance from Error in LLM Hallucinations.
CoRR, 2024
Constructing Benchmarks and Interventions for Combating Hallucinations in LLMs.
CoRR, 2024
Interpreting Embedding Spaces by Conceptualization.
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, 2023