Showing cs.AIShow all
2 papers · 1 filter
cs.AI2026
SciLitBench: Benchmark and Design Principles for LLM-Powered Systematic Literature Reviews
Miguel Zabaleta, Baihan Lin
Systematic reviews require sustained human judgment across thousands of records, yet existing evaluations of large language models (LLMs) typically examine review stages in isolati…
cs.AI2024
Simulating Tabular Datasets through LLMs to Rapidly Explore Hypotheses about Real-World Entities
Miguel Zabaleta, Joel Lehman
Do horror writers have worse childhoods than other writers? Though biographical details are known about many writers, quantitatively exploring such a qualitative hypothesis require…