LGAR combines zero-shot LLM graded relevance scoring with monoT5 re-ranking to rank abstracts for systematic reviews, outperforming QA-based baselines by 5-10 pp MAP on two benchmarks.
Title resolution pending
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
-
LGAR: Zero-Shot LLM-Guided Neural Ranking for Abstract Screening in Systematic Literature Reviews
LGAR combines zero-shot LLM graded relevance scoring with monoT5 re-ranking to rank abstracts for systematic reviews, outperforming QA-based baselines by 5-10 pp MAP on two benchmarks.