Large Language Models (LLMs) perform well on standard reasoning and question-answering benchmarks, yet such evaluations often fail to capture their ability to handle long-tail, expertise-intensive knowledge in real-world professional scenarios. We introduce LPFQA, a long-tail knowledge benchmark derived from authentic professional forum discussions, covering 7 academic and industrial domains with 430 curated tasks grounded in practical expertise. LPFQA evaluates specialized reasoning, domain-specific terminology understanding, and contextual interpretation, and adopts a hierarchical difficulty structure to ensure semantic clarity and uniquely identifiable answers. Experiments on over multiple mainstream LLMs reveal substantial performance gaps, particularly on tasks requiring deep domain reasoning, exposing limitations overlooked by existing benchmarks. Overall, LPFQA provides an authentic and discriminative evaluation framework that complements prior benchmarks and informs future LLM development.
@article{arxiv.2511.06346,
title = {LPFQA: A Long-Tail Professional Forum-based Benchmark for LLM Evaluation},
author = {Liya Zhu and Peizhuang Cong and Jingzhe Ding and Aowei Ji and Wenya Wu and Jiani Hou and Chunjie Wu and Xiang Gao and Jingkai Liu and Zhou Huan and Xuelei Sun and Yang Yang and Jianpeng Jiao and Liang Hu and Xinjie Chen and Jiashuo Liu and Tong Yang and Zaiyuan Wang and Ge Zhang and Wenhao Huang},
journal= {arXiv preprint arXiv:2511.06346},
year = {2026}
}