In the final post of the Adaptive RAG series, we explore how to treat selective retrieval as a core, learned skill, moving from passive observation to active, intelligent decision-making.
CorporateBench: Large-Scale Q&A Benchmarking with Temporal Knowledge Bases
@srhm_ca et al. present an enterprise Q&A benchmark built from synthetic companies with consistent knowledge bases.
๐ arxiv.org/abs/2608.27391
๐ค huggingface.co/datasets/epiq-โฆ
Unifying Search and Recommendation with Dual-View Representation Learning in a Generative Paradigm
@JZhao0109 et a. unifiy search and recommendation in a generative model via task prompts and dual CF/semantic views.
๐ doi.org/10.1145/3841470
๐จ๐ฝโ๐ป github.com/Polaris-JZ/Genโฆ