Asymptotics of Language Model Alignmentby Joy Qiping Yang, Salman Salamatian, Ziteng Sun, Ananda Theertha Suresh,…
Propensity Score Alignment of Unpaired Multimodal Databy Johnny Xi, Jana Osea, Zuheng Xu, Jason HartfordFirst…
Evaluating Text-to-Visual Generation with Image-to-Text Generationby Zhiqiu Lin, Deepak Pathak, Baiqi Li, Jiayao Li, Xide…
Evaluating the Factuality of Large Language Models using Large-Scale Knowledge Graphsby Xiaoze Liu, Feijie Wu,…
What is in Your Safe Data? Identifying Benign Data that Breaks Safetyby Luxi He, Mengzhou…
Comparing Bad Apples to Good Oranges: Aligning Large Language Models via Joint Preference Optimizationby Hritik…
Extensive Self-Contrast Enables Feedback-Free Language Model Alignmentby Xiao Liu, Xixuan Song, Yuxiao Dong, Jie TangFirst…
FairRAG: Fair Human Generation via Fair Retrieval Augmentationby Robik Shrestha, Yang Zou, Qiuyu Chen, Zhiheng…
Dual-Personalizing Adapter for Federated Foundation Modelsby Yiyuan Yang, Guodong Long, Tao Shen, Jing Jiang, Michael…
Understanding the Learning Dynamics of Alignment with Human Feedbackby Shawn Im, Yixuan LiFirst submitted to…