Saved in:
Bibliographic Details
Main Authors: Song, Wentang, Li, Jinqiang, Huang, Kele, Lin, Junhui, Wu, Shengxiang, Xie, Zhongshi
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2601.03272
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914237530505216
author Song, Wentang
Li, Jinqiang
Huang, Kele
Lin, Junhui
Wu, Shengxiang
Xie, Zhongshi
author_facet Song, Wentang
Li, Jinqiang
Huang, Kele
Lin, Junhui
Wu, Shengxiang
Xie, Zhongshi
contents The versatility of Large Language Models (LLMs) in vertical domains has spurred the development of numerous specialized evaluation benchmarks. However, these benchmarks often suffer from significant semantic redundancy and impose high computational costs during evaluation. Existing compression methods, such as tinyBenchmarks depend critically on correctness labels from multiple historical models evaluated on the full test set, making them inapplicable in cold-start scenarios, such as the introduction of a new task, domain, or model with no prior evaluation history. To address this limitation, we propose a history-free test set compression framework that requires no prior model performance data. Our method begins by fine-tuning a base LLM on a small amount of domain-specific data to internalize task-relevant semantics. It then generates high-level semantic embeddings for all original test samples using only their raw textual content. In this domain-adapted embedding space, we perform task-aware clustering and introduce a novel dataset X-ray mechanism that analyzes cluster geometry to dynamically calibrate the compression intensity based on the intrinsic redundancy of the benchmark. Experiments on professional-domain dataset, notably a large-scale 3GPP communications benchmark, demonstrate that our approach effectively identifies and removes redundant samples, reducing evaluation cost by over 90% while preserving high fidelity to the full benchmark.
format Preprint
id arxiv_https___arxiv_org_abs_2601_03272
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Less is more: Not all samples are effective for evaluation
Song, Wentang
Li, Jinqiang
Huang, Kele
Lin, Junhui
Wu, Shengxiang
Xie, Zhongshi
Computation and Language
Artificial Intelligence
The versatility of Large Language Models (LLMs) in vertical domains has spurred the development of numerous specialized evaluation benchmarks. However, these benchmarks often suffer from significant semantic redundancy and impose high computational costs during evaluation. Existing compression methods, such as tinyBenchmarks depend critically on correctness labels from multiple historical models evaluated on the full test set, making them inapplicable in cold-start scenarios, such as the introduction of a new task, domain, or model with no prior evaluation history. To address this limitation, we propose a history-free test set compression framework that requires no prior model performance data. Our method begins by fine-tuning a base LLM on a small amount of domain-specific data to internalize task-relevant semantics. It then generates high-level semantic embeddings for all original test samples using only their raw textual content. In this domain-adapted embedding space, we perform task-aware clustering and introduce a novel dataset X-ray mechanism that analyzes cluster geometry to dynamically calibrate the compression intensity based on the intrinsic redundancy of the benchmark. Experiments on professional-domain dataset, notably a large-scale 3GPP communications benchmark, demonstrate that our approach effectively identifies and removes redundant samples, reducing evaluation cost by over 90% while preserving high fidelity to the full benchmark.
title Less is more: Not all samples are effective for evaluation
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2601.03272