Himabindu Lakkaraju
12 papers · 863 citations
Most-cited papers
- Certifying LLM Safety Against Adversarial Prompting2023 · 305 citations
- In-context Unlearning: Language Models As Few Shot Unlearners2023 · 212 citations
- Faithfulness Vs. Plausibility: On The (un)reliability Of Explanations From Large Language Models2024 · 107 citations
- Follow My Instruction And Spill The Beans: Scalable Data Extraction From Retrieval-augmented Generation Systems2024 · 63 citations
- Quantifying Uncertainty In Natural Language Explanations Of Large Language Models2023 · 36 citations
Topics