2 papers
cs.AI2026
CME-SpectrumBench: Can LLMs Analyze Condensed Matter Spectral Data?
Jin Gene Wong, Anjney Midha, Joseph Mathew Tennyson +3
Large Language Models (LLMs) are presently well assessed by expert-level mathematics and physics benchmarks which focus on theoretical, symbolic reasoning. However, we lack experim…
cs.AI2026
MoMaTune: Model, Match, Then Tune Language Models for Numerical Records
Weimin Lyu, Jingfen Zhang, Lingdao Sha +4
Despite remarkable progress in language understanding and generation, decoder language models continue to exhibit striking failures on numerical data. Numerical examples are typica…