Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Mahmoud Said

Mahmoud Said

1 indexed paper

Recent (6 mo)
1
With code
0
Influential cites
0
Benchmarked
0

Publications per year

1
26

Top categories

NLP×1Info Retrieval×1

Frequent co-authors

Mahmoud Hany1×
Mourad ElSheraey1×
Peter Naoum1×

Research Timeline

2026
Inject or Navigate? Token-Efficient Retrieval for LLM Analysis of Transactional Legal Documents

This paper compares three methods for answering questions over legal documents: full-corpus injection, embedding retrieval, and LLM navigation over a compact structured index. The results show that the last two methods have lower token footprint, smaller answering context, and lower dollar cost than full-corpus injection.

Highlighted terms show continued research focus across papers

Papers

cs.CLcs.IREmpiricalRecentJul 7, 2026

Inject or Navigate? Token-Efficient Retrieval for LLM Analysis of Transactional Legal Documents

Mahmoud Hany, Mourad ElSheraey, Mahmoud Said, Peter Naoum

This paper compares three methods for answering questions over legal documents: full-corpus injection, embedding retrieval, and LLM navigation over a compact structured index. The results show that th…

View →