4 papers
LaRA: Layer-wise Representation Analysis for Detecting Data Contamination in RL Post-Training
Minju Gwak, Minseo Kwak, Dongseok Lee +3
Reinforcement learning (RL) post-training has shown to improve reasoning in large language models (LLMs). However, there has been little exploration on the problem of data contamin…
Tree-based Dialogue Reinforced Policy Optimization for Red-Teaming Attacks
Ruohao Guo, Afshin Oroojlooy, Roshan Sridhar +3
Despite recent rapid progress in AI safety, current large language models remain vulnerable to adversarial attacks in multi-turn interaction settings, where attackers strategically…
Auditing Language Model Unlearning via Information Decomposition
Anmol Goel, Alan Ritter, Iryna Gurevych
We expose a critical limitation in current approaches to machine unlearning in language models: despite the apparent success of unlearning algorithms, information about the forgott…
Semantic Differentiation for Tackling Challenges in Watermarking Low-Entropy Constrained Generation Outputs
Nghia T. Le, Alan Ritter, Kartik Goyal
We demonstrate that while the current approaches for language model watermarking are effective for open-ended generation, they are inadequate at watermarking LM outputs for constra…