1
V-FiLLM: Verified Financial LLM Reasoning Benchmark
首个面向金融推理的可验证基准,用可执行计算树生成测试,直击LLM结构化数据推理短板。
arXiv:2608.11047v1 Announce Type: cross Abstract: While existing benchmarks have made substantial progress in evaluating LLMs across STEM domains, fin…