GMP-AR: Granularity Message Passing and Adaptive Reconciliation for Temporal Hierarchy Forecastingby Fan Zhou, Chen Pan,…
Is poisoning a real threat to LLM alignment? Maybe more so than you thinkby Pankayaraj…
Dialogue Action Tokens: Steering Language Models in Goal-Directed Dialogue with a Multi-Turn Plannerby Kenneth Li,…
Sparsity-Constraint Optimization via Splicing Iterationby Zezhi Wang, Jin Zhu, Junxian Zhu, Borui Tang, Hongmei Lin,…
Iterative Length-Regularized Direct Preference Optimization: A Case Study on Improving 7B Language Models to GPT-4…
WPO: Enhancing RLHF with Weighted Preference Optimizationby Wenxuan Zhou, Ravi Agrawal, Shujian Zhang, Sathish Reddy…
Optimizing Instructions and Demonstrations for Multi-Stage Language Model Programsby Krista Opsahl-Ong, Michael J Ryan, Josh…
Measuring memorization in RLHF for code completionby Aneesh Pappu, Billy Porter, Ilia Shumailov, Jamie HayesFirst…
To Clip or not to Clip: the Dynamics of SGD with Gradient Clipping in High-Dimensionsby…
Linear Bellman Completeness Suffices for Efficient Online Reinforcement Learning with Few Actionsby Noah Golowich, Ankur…