Apr 24, 2025 Steering the CensorShip: Uncovering Representation Vectors for LLM "Thought" Control Aug 10, 2024 The Mismeasure of Man and Models Aug 17, 2023 Adjectives Can Reveal Gender Biases Within NLP Models Nov 13, 2022 Balancing Tradeoffs between Fickleness and Obstinacy in NLP Models