Disentangling Likes and Dislikes in Personalized Generative Explainable Recommendationby Ryotaro Shimizu, Takashi Wada, Yu Wang,…
A Simplifying and Learnable Graph Convolutional Attention Network for Unsupervised Knowledge Graphs Alignmentby Weishan Cai,…
A theoretical perspective on mode collapse in variational inferenceby Roman Soletskyi, Marylou Gabrié, Bruno LoureiroFirst…
Reverse-Engineering the Readerby Samuel Kiegeland, Ethan Gotlieb Wilcox, Afra Amini, David Robert Reich, Ryan CotterellFirst…
Language Model Preference Evaluation with Multiple Weak Evaluatorsby Zhengyu Hu, Jieyu Zhang, Zhihan Xiong, Alexander…
Towards More Effective Table-to-Text Generation: Assessing In-Context Learning and Self-Evaluation with Open-Source Modelsby Sahar Iravani,…
Rethinking Misalignment in Vision-Language Model Adaptation from a Causal Perspectiveby Yanan Zhang, Jiangmeng Li, Lixiang…
ELF-Gym: Evaluating Large Language Models Generated Features for Tabular Predictionby Yanlin Zhang, Ning Li, Quan…
Weak-to-Strong Generalization beyond Accuracy: a Pilot Study in Safety, Toxicity, and Legal Reasoningby Ruimeng Ye,…
Embedding an Ethical Mind: Aligning Text-to-Image Synthesis via Lightweight Value Optimizationby Xingqi Wang, Xiaoyuan Yi,…