#artificial intelligence
Sep 2026
Highlight-Then-Summarize: Learning to Compress Evidence for Long-Context Understanding
The results show that explicitly selecting and integrating evidence improves long-context reasoning while enabling more compact generation, and the strongest overall result among the evaluated open-source models is obtained.
Zhao-Yuan Xia, Qinghongbing Xie, Yung Xiang Hue et al.
· arXiv.org · 0 citations