AIIC AI Intelligence Centre

SOURCE-LINKED INTELLIGENCE

SciLitBench: Benchmark and Design Principles for LLM-Powered Systematic Literature Reviews

arXiv · AI, language, vision and robotics · article · Aug 29, 2026 · UTC

Systematic reviews require sustained human judgment across thousands of records, yet existing evaluations of large language models (LLMs) typically examine review stages in isolation. We introduce SciLitBench, a multi-stage benchmark spanning title and abstract screening, full-text screening, and schema-guided data extraction, with 42,981 retrieved records, 1,012 full texts, and annotations for 888 included papers. Across 22 open-weight LLMs from six model families, explicit inclusion and exclusion criteria improve title and abstract screening $F_2$ by 28.8\%, while researcher-authored rationa

Read original source ↗ Open in workspace

recordType
paper
region
Global

Evidence & attribution

First collected: 2026-09-21T08:02:06.831Z. This is not the publication date.