Highlight-Then-Summarize: Learning to Compress Evidence for Long-Context Understanding
Long-context understanding requires large language models (LLMs) to reason over lengthy documents, conversations, and code, yet task-relevant evidence is often sparse and scattered amid substantial irrelevant and redundant content. We propose Highlight-Then-Summarize (H2S), a compress-then-reason paradigm that first id...
Zhao-Yuan Xia, Qinghongbing Xie, Yung Xiang Hue et al.
· 0 citations