WirelessMathBench, a 587-question benchmark drawn from 40 wireless communications papers, finds that leading LLMs score only 38.05% on average and 7.83% on full equation completion, revealing weak symbolic derivation ability.
IEEE Wireless Com- munications, 31(3):140–147
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
-
WirelessMathBench: A Mathematical Modeling Benchmark for LLMs in Wireless Communications
WirelessMathBench, a 587-question benchmark drawn from 40 wireless communications papers, finds that leading LLMs score only 38.05% on average and 7.83% on full equation completion, revealing weak symbolic derivation ability.