Kavli Affiliate: Xiang Zhang | First 5 Authors: Jiaqi Wei, Hao Zhou, Xiang Zhang, Di Zhang, Zijie Qiu | Summary: Retrieval-augmented generation (RAG) has emerged as a foundational paradigm for knowledge-grounded text generation. However, existing RAG pipelines often fail to ensure that the reasoning trajectories align with the evidential constraints imposed by retrieved content. In […]
Continue.. AlignRAG: An Adaptable Framework for Resolving Misalignments in Retrieval-Aware Reasoning of RAG