The authors developed Highlight-Then-Summarize, or H2S, a compress-then-reason procedure for documents, conversations, and code.
Selecting evidence before summarizing improves long-context reasoning efficiency
A 14-billion-parameter model trained to extract and compress relevant passages outperformed larger open-source models while using shorter outputs.
Chinese Tech
Zhaoyuan Xia (Peking University) · Qinghongbing Xie (Tsinghua University) · Yung Xiang Hue (Tsinghua University) · Jianguang Jiang (Baidu Inc) · Gaofeng Lu (Baidu Inc) · Zhenyu Jiao (Baidu Inc) · +4 more
Research Digest··2 min read
Xia et al.
Why this paper
From Baidu Inc. and 2 others · Part of Context Engineering for Agents, now 30 papers
In one line
Highlight-Then-Summarize compresses evidence by selecting and summarizing before answering, improving long-context reasoning.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ·No stated limitations found
- ✓Reports numbers on named benchmarks
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§