Less is more: Not all samples are effective for evaluation

• URL: http://arxiv.org/abs/2601.03272v1
• Date: Mon, 22 Dec 2025 08:04:05 GMT
• Title: Less is more: Not all samples are effective for evaluation
• Authors: Wentang Song, Jinqiang Li, Kele Huang, Junhui Lin, Shengxiang Wu, Zhongshi Xie,
• Abstract summary: Existing compression methods depend on correctness labels from multiple historical models evaluated on the full test set.<n>We propose a history-free test set compression framework that requires no prior model performance data.<n>Our approach effectively identifies and removes redundant samples, reducing evaluation cost by over 90%.
• Score: 1.6456338609651404
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• DEP: A Decentralized Large Language Model Evaluation Protocol [51.3646001384887]
  Decentralized Evaluation Protocol (DEP) is a decentralized yet unified and standardized evaluation framework.<n>By decoupling users, LLMs, and benchmarks, DEP enables modular, plug-and-play evaluation.<n>We develop DEP Toolkit, a protocol-compatible toolkit that supports features such as breakpoint resume, concurrent requests, and congestion control.
  arXiv  Detail & Related papers  (2026-03-01T16:10:16Z)
• Learning More from Less: Unlocking Internal Representations for Benchmark Compression [37.69575776639016]
  We introduce REPCORE, which aligns heterogeneous hidden states into a unified latent space to construct representative coresets.<n>Experiments on five benchmarks and over 200 models show consistent gains over output-based baselines in ranking correlation and estimation accuracy.
  arXiv  Detail & Related papers  (2026-01-31T13:11:39Z)
• Scales++: Compute Efficient Evaluation Subset Selection with Cognitive Scales Embeddings [23.9553588103042]
  We propose a item-centric approach to benchmark subset selection, arguing that selection should be based on the intrinsic properties of the task items themselves.<n>We show Scales++ reduces the upfront selection cost by over 18x while achieving competitive predictive fidelity.<n>We demonstrate that this item-centric approach enables more efficient model evaluation without significant fidelity degradation.
  arXiv  Detail & Related papers  (2025-10-30T11:28:58Z)
• Test-Time Adaptive Object Detection with Foundation Model [39.96498227103011]
  We propose the first foundation model-powered test-time adaptive object detection method.<n>We design a Multi-modal Prompt-based Mean-Teacher framework for vision-language detector-driven test-time adaptation.<n>To guarantee high-quality pseudo-labels in every test batch, we maintain an Instance Dynamic Memory.
  arXiv  Detail & Related papers  (2025-10-29T05:19:38Z)
• Rethinking LLM Evaluation: Can We Evaluate LLMs with 200x Less Data? [82.09573568241724]
  EssenceBench is a coarse-to-fine framework utilizing an iterative Genetic Algorithm (GA)<n>Our approach yields superior compression results with lower reconstruction error and markedly higher efficiency.<n>On the HellaSwag benchmark (10K samples), our method preserves the ranking of all models shifting within 5% using 25x fewer samples, and achieves 95% ranking preservation shifting within 5% using only 200x fewer samples.
  arXiv  Detail & Related papers  (2025-10-12T05:38:10Z)
• TestAgent: Automatic Benchmarking and Exploratory Interaction for Evaluating LLMs in Vertical Domains [19.492393243160244]
  Large Language Models (LLMs) are increasingly deployed in highly specialized vertical domains.<n>Existing evaluations for vertical domains typically rely on the labor-intensive construction of static single-turn datasets.<n>We propose TestAgent, a framework for automatic benchmarking and exploratory dynamic evaluation in vertical domains.
  arXiv  Detail & Related papers  (2024-10-15T11:20:42Z)
• A CLIP-Powered Framework for Robust and Generalizable Data Selection [51.46695086779598]
  Real-world datasets often contain redundant and noisy data, imposing a negative impact on training efficiency and model performance.<n>Data selection has shown promise in identifying the most representative samples from the entire dataset.<n>We propose a novel CLIP-powered data selection framework that leverages multimodal information for more robust and generalizable sample selection.
  arXiv  Detail & Related papers  (2024-10-15T03:00:58Z)
• LiveXiv -- A Multi-Modal Live Benchmark Based on Arxiv Papers Content [62.816876067499415]
  We propose LiveXiv: a scalable evolving live benchmark based on scientific ArXiv papers.<n>LiveXiv accesses domain-specific manuscripts at any given timestamp and proposes to automatically generate visual question-answer pairs.<n>We benchmark multiple open and proprietary Large Multi-modal Models (LMMs) on the first version of our benchmark, showing its challenging nature and exposing the models true abilities.
  arXiv  Detail & Related papers  (2024-10-14T17:51:23Z)
• Learning Feature Inversion for Multi-class Anomaly Detection under General-purpose COCO-AD Benchmark [101.23684938489413]
  Anomaly detection (AD) is often focused on detecting anomalies for industrial quality inspection and medical lesion examination. This work first constructs a large-scale and general-purpose COCO-AD dataset by extending COCO to the AD field. Inspired by the metrics in the segmentation field, we propose several more practical threshold-dependent AD-specific metrics.
  arXiv  Detail & Related papers  (2024-04-16T17:38:26Z)
• Automating Dataset Updates Towards Reliable and Timely Evaluation of Large Language Models [81.27391252152199]
  Large language models (LLMs) have achieved impressive performance across various natural language benchmarks. We propose to automate dataset updating and provide systematic analysis regarding its effectiveness. There are two updating strategies: 1) mimicking strategy to generate similar samples based on original data, and 2) extending strategy that further expands existing samples.
  arXiv  Detail & Related papers  (2024-02-19T07:15:59Z)
• Large-scale Fully-Unsupervised Re-Identification [78.47108158030213]
  We propose two strategies to learn from large-scale unlabeled data. The first strategy performs a local neighborhood sampling to reduce the dataset size in each without violating neighborhood relationships. A second strategy leverages a novel Re-Ranking technique, which has a lower time upper bound complexity and reduces the memory complexity from O(n2) to O(kn) with k n.
  arXiv  Detail & Related papers  (2023-07-26T16:19:19Z)
• Small but Mighty: New Benchmarks for Split and Rephrase [18.959219419951083]
  Split and Rephrase is a text simplification task of rewriting a complex sentence into simpler ones. We find that the widely used benchmark dataset universally contains easily exploitable syntactic cues. We show that even a simple rule-based model can perform on par with the state-of-the-art model.
  arXiv  Detail & Related papers  (2020-09-17T23:37:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.