Intelligence and Knowledge Discovery Research Lab @ USC

The Intelligence and Knowledge Discovery (INK) Lab at USC studies how large language models reason, explain themselves, work alongside people, and how to make them more trustworthy. Our recent work spans reasoning over rules and long chains of thought, interpretability and accountability (memorization, forgetting, backdoors, and model signatures), explanations that help people learn and rely on AI appropriately, and the evaluation of language agents and cultural bias in language models. We are excited about both developing computational models and building practical systems for real-world applications. Led by Prof. Xiang Ren, the INK lab is also part of USC Machine Learning Center, NLP Community@USC, and ISI Center on Knowledge Graphs.