SCAN: Structured Capability Assessment and Navigation for LLMs

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Wang, Zongqi, Gu, Tianle, Gong, Chen, Tian, Xin, Bao, Siqi, Yang, Yujiu
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910181738151936
author Wang, Zongqi
Gu, Tianle
Gong, Chen
Tian, Xin
Bao, Siqi
Yang, Yujiu
author_facet Wang, Zongqi
Gu, Tianle
Gong, Chen
Tian, Xin
Bao, Siqi
Yang, Yujiu
contents Evaluating Large Language Models (LLMs) has become increasingly important, with automatic evaluation benchmarks gaining prominence as alternatives to human evaluation. While existing research has focused on approximating model rankings, such benchmarks fail to provide users and developers with a comprehensive and fine-grained understanding of a specific model's capabilities. To fill this gap, we propose \textbf{SCAN} (Structured Capability Assessment and Navigation), a practical framework that enables detailed characterization of LLM capabilities through comprehensive and fine-grained evaluation. SCAN incorporates four key components: (1) TaxBuilder, which extracts capability-indicating tags from extensive queries to construct a hierarchical taxonomy automatically; (2) RealMix, a query synthesis and filtering mechanism that ensures sufficient evaluation data for each capability tag; (3) a suite of visualization and analysis tools that facilitate efficient navigation and analysis of model capabilities; and (4) a PC$^2$-based (Pre-Comparison-derived Criteria) LLM-as-a-Judge approach that achieves significantly higher accuracy compared to classic LLM-as-a-Judge method. Using SCAN, we conduct a comprehensive evaluation of 21 mainstream LLMs. Our detailed analysis of the GPT-OSS family reveals substantial performance variations, even within sub-capabilities belonging to the same category of capability. This finding highlights the importance of fine-grained evaluation in accurately understanding LLM behavior. Project homepage and resources are available at \href{https://github.com/liudan193/SCAN}{https://github.com/liudan193/SCAN}.
format Preprint
id arxiv_https___arxiv_org_abs_2505_06698
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SCAN: Structured Capability Assessment and Navigation for LLMs
Wang, Zongqi
Gu, Tianle
Gong, Chen
Tian, Xin
Bao, Siqi
Yang, Yujiu
Computation and Language
Evaluating Large Language Models (LLMs) has become increasingly important, with automatic evaluation benchmarks gaining prominence as alternatives to human evaluation. While existing research has focused on approximating model rankings, such benchmarks fail to provide users and developers with a comprehensive and fine-grained understanding of a specific model's capabilities. To fill this gap, we propose \textbf{SCAN} (Structured Capability Assessment and Navigation), a practical framework that enables detailed characterization of LLM capabilities through comprehensive and fine-grained evaluation. SCAN incorporates four key components: (1) TaxBuilder, which extracts capability-indicating tags from extensive queries to construct a hierarchical taxonomy automatically; (2) RealMix, a query synthesis and filtering mechanism that ensures sufficient evaluation data for each capability tag; (3) a suite of visualization and analysis tools that facilitate efficient navigation and analysis of model capabilities; and (4) a PC$^2$-based (Pre-Comparison-derived Criteria) LLM-as-a-Judge approach that achieves significantly higher accuracy compared to classic LLM-as-a-Judge method. Using SCAN, we conduct a comprehensive evaluation of 21 mainstream LLMs. Our detailed analysis of the GPT-OSS family reveals substantial performance variations, even within sub-capabilities belonging to the same category of capability. This finding highlights the importance of fine-grained evaluation in accurately understanding LLM behavior. Project homepage and resources are available at \href{https://github.com/liudan193/SCAN}{https://github.com/liudan193/SCAN}.
title SCAN: Structured Capability Assessment and Navigation for LLMs
topic Computation and Language
url https://arxiv.org/abs/2505.06698