2 papers
cs.AI2026
More Than Can Be Said: A Benchmark and Framework for Pre-Question Scientific Ideation
Jie Yu, Song Qiu
AI research agents have shown strong potential in automating literature search and manuscript refinement, yet most assume a clear and actionable initial input, operating only after…
cs.CL2026
A Mechanism and Optimization Study on the Impact of Information Density on User-Generated Content Named Entity Recognition
Jiang Xiaobo, Dinghong Lai, Song Qiu +2
Named Entity Recognition (NER) models trained on clean, high-resource corpora exhibit catastrophic performance collapse when deployed on noisy, sparse User-Generated Content (UGC),…