Publications
Scientific publications are the most important measure of our academic excellence and impact. In the past years, CISPA researchers have published many papers at scientific top-tier conferences and in prestigious journals. Our publications are listed in our publications database, including a link to the original paper.
NeurIPS-Workshop (NeurIPS-W) Beyond Steering: Evaluating Fine-Grained and Multi-Concept Control in LLMs Proceedings Article
NeurIPS-Workshop (NeurIPS-W) Can LLMs Propose Instrumental Variables for Causal Reasoning?
Theory of Cryptography Conference (TCC) Separating Pseudorandom Codes from Local Oracles
International Colloquium on Automata Languages and Programming (ICALP) Robust Contraction Decomposition for Minor-Free Graphs and its Applications
Conference on Neural Information Processing Systems (NeurIPS) Adjacent Words, Divergent Intents: Jailbreaking Large Language Models via Task Concurrency
Conference on Neural Information Processing Systems (NeurIPS) An Analysis of Causal Effect Estimation using Outcome Invariant Data Augmentation
International Conference on Principles of Distributed Systems (OPODIS) Distributed Download from an External Data Source in Asynchronous Faulty Settings
Conference on Neural Information Processing Systems (NeurIPS) Pay Attention to Small Weights
Conference on Neural Information Processing Systems (NeurIPS) Finding and Reactivating Post-Trained LLMs’ Hidden Safety Mechanisms