SARESG prunes documents to aspect-relevant sentences via embedding similarity before LLM summarization, reporting gains over selective-context baselines on three datasets.
A sentence is known by the company it keeps: Improving legal document summarization using deep clustering,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Aspect-Based Summarization with Self-Aspect Retrieval Enhanced Generation
SARESG prunes documents to aspect-relevant sentences via embedding similarity before LLM summarization, reporting gains over selective-context baselines on three datasets.