Saved in:
Bibliographic Details
Main Authors: Zhu, Liya, Cong, Peizhuang, Ding, Jingzhe, Ji, Aowei, Wu, Wenya, Hou, Jiani, Wu, Chunjie, Gao, Xiang, Liu, Jingkai, Huan, Zhou, Sun, Xuelei, Yang, Yang, Jiao, Jianpeng, Hu, Liang, Chen, Xinjie, Liu, Jiashuo, Yang, Tong, Wang, Zaiyuan, Zhang, Ge, Huang, Wenhao
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.06346
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914239040454656
author Zhu, Liya
Cong, Peizhuang
Ding, Jingzhe
Ji, Aowei
Wu, Wenya
Hou, Jiani
Wu, Chunjie
Gao, Xiang
Liu, Jingkai
Huan, Zhou
Sun, Xuelei
Yang, Yang
Jiao, Jianpeng
Hu, Liang
Chen, Xinjie
Liu, Jiashuo
Yang, Tong
Wang, Zaiyuan
Zhang, Ge
Huang, Wenhao
author_facet Zhu, Liya
Cong, Peizhuang
Ding, Jingzhe
Ji, Aowei
Wu, Wenya
Hou, Jiani
Wu, Chunjie
Gao, Xiang
Liu, Jingkai
Huan, Zhou
Sun, Xuelei
Yang, Yang
Jiao, Jianpeng
Hu, Liang
Chen, Xinjie
Liu, Jiashuo
Yang, Tong
Wang, Zaiyuan
Zhang, Ge
Huang, Wenhao
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2511_06346
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LPFQA: A Long-Tail Professional Forum-based Benchmark for LLM Evaluation
Zhu, Liya
Cong, Peizhuang
Ding, Jingzhe
Ji, Aowei
Wu, Wenya
Hou, Jiani
Wu, Chunjie
Gao, Xiang
Liu, Jingkai
Huan, Zhou
Sun, Xuelei
Yang, Yang
Jiao, Jianpeng
Hu, Liang
Chen, Xinjie
Liu, Jiashuo
Yang, Tong
Wang, Zaiyuan
Zhang, Ge
Huang, Wenhao
Artificial Intelligence
Computation and Language
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.
title LPFQA: A Long-Tail Professional Forum-based Benchmark for LLM Evaluation
topic Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2511.06346