Generate-then-rank is a widely used mechanism for text generation, where a generator produces multiple text candidates and a ranker chooses the best one among the text candidates. However, existing methods usually train the generator and the ranker individually, neglecting the mutual feedback that could further enhance the generation quality. To tackle this limitation, we propose JGR, a novel joint training algorithm that integrates the generator and the ranker in a single framework. JGR optimizes the generator with a hybrid objective that combines data likelihood and ranker reward, and trains the ranker with a contrastive loss that compares the generator outputs. By iteratively updating the generator and the ranker, JGR can effectively harmonize their learning and enhance their quality jointly. We evaluate JGR on various text generation tasks and demonstrate that it surpasses existing methods on four public datasets across three common generation scenarios. Our code and models are publicly available at https://github.com/microsoft/ProphetNet/tree/master/JGR.
Large Language Models are Zero-Shot Rankers for Recommender Systems
Gaoling School of Artificial Intelligence, Renmin University of China(中国人民大学高瓴人工智能学院);UC San Diego(加州大学圣迭戈分校);School of Information, Renmin University of China(中国人民大学信息资源管理学院);WeChat, Tencent(腾讯微信)
Multimodal Generative Engine Optimization: Rank Manipulation for Vision-Language Model Rankers
Georgetown University(乔治城大学);University of Southern California(南加州大学);University of Maryland, College Park(马里兰大学学院公园分校);Arizona State University(亚利桑那州立大学)
CAR: Query-Guided Confidence-Aware Reranking for Retrieval-Augmented Generation
School of Computer Science and Technology, Dalian University of Technology(大连理工大学计算机科学与技术学院);School of Information Engineering, Dalian Ocean University(大连海洋大学信息工程学院);School of Information Engineering, Liaodong University(辽东学院信息工程学院);Information Technology Center, Qinghai University(青海大学信息技术中心);College of Health-Preservation and Wellness, Dalian Medical University(大连医科大学养生与健康学院);Tencent(腾讯)