Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Erasing Conceptual Knowledge from Language ModelsAnthropic · neural information processing systems1 citationJan 1, 2025Quantifying Elicitation of Latent Capabilities in Language ModelsAnthropic, OpenAI · neural information processing systemsJan 1, 2025Better Training Data Attribution via Better Inverse Hessian-Vector ProductsAnthropic · neural information processing systemsJan 1, 2025Training Language Models to Generate Quality Code with Program Analysis FeedbackAnthropic, Google DeepMind, Microsoft · neural information processing systemsJan 1, 2025IF-Guide: Influence Function-Guided Detoxification of LLMsAnthropic, Google DeepMind · neural information processing systemsJan 1, 2025Datasets, Documents, and Repetitions: The Practicalities of Unequal Data QualityAllen Institute for AI, Anthropic, OpenAI · neural information processing systemsJan 1, 2025Noise Injection Reveals Hidden Capabilities of Sandbagging Language ModelsAnthropic · neural information processing systemsJan 1, 2025