LitXBench: A Benchmark for Extracting Experiments from Scientific Literature
This work addresses the need for better data extraction tools to support materials scientists in building property prediction models and facilitating discovery, though it is incremental as it focuses on benchmarking and a specific domain.
The paper tackles the problem of extracting experimental data from scientific literature by introducing LitXBench, a benchmarking framework, and LitXAlloy, a dense benchmark with 1426 measurements from 19 alloy papers, finding that frontier language models outperform existing extraction pipelines by up to 0.37 F1.
Aggregating experimental data from papers enables materials scientists to build better property prediction models and to facilitate scientific discovery. Recently, interest has grown in extracting not only single material properties but also entire experimental measurements. To support this shift, we introduce LitXBench, a framework for benchmarking methods that extract experiments from literature. We also present LitXAlloy, a dense benchmark comprising 1426 total measurements from 19 alloy papers. By storing the benchmark's entries as Python objects, rather than text-based formats such as CSV or JSON, we improve auditability and enable programmatic data validation. We find that frontier language models, such as Gemini 3.1 Pro Preview, outperform existing multi-turn extraction pipelines by up to 0.37 F1. Our results suggest that this performance gap arises because extraction pipelines associate measurements with compositions rather than the processing steps that define a material.