TreeReview builds a dynamic tree of review questions, answers leaves with retrieved paper chunks, and aggregates upward to produce reviews that outperform baselines while cutting token use by 80%.
InProceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Vol- ume 1: Long Papers), pages 1658–1677, Bangkok, Thailand
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
-
TreeReview: A Dynamic Tree of Questions Framework for Deep and Efficient LLM-based Scientific Peer Review
TreeReview builds a dynamic tree of review questions, answers leaves with retrieved paper chunks, and aggregates upward to produce reviews that outperform baselines while cutting token use by 80%.