arXiv AI June 4, 2026 By Trinh Pham, Viet Huynh, Hongzhi Yin, Quoc Viet Hung Nguyen, Thanh Tam Nguyen

Learning to Evaluate: Cost-Effective Model Evaluation on Unlabeled Data with Meta-Learning

arXiv:2605. 23595v2 Announce Type: replace-cross Abstract: The rapid advancement of machine learning has led to an unprecedented expansion of model ecosystems, making it increasingly difficult to assess the reliability of newly released models on unseen and unlabeled data.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv Machine Learning

Jul 7

Labeled-Data-Free Meta-Learning: Efficient Task Generation Using Pre-trained Models and Unlabeled Data

arXiv:2607. 02850v1 Announce Type: new Abstract: Meta-learning without labeled data is crucial for real-world applications, where obtaining labeled datasets can be expensive or restricted due to privacy concerns.

By Lei Sun, Yusuke Tanaka, Tomoharu Iwata

benchmarks safety

arXiv Machine Learning

Aug 18

Limits to scalable evaluation at the frontier: LLM as Judge won't beat twice the data

arXiv:2410. 13341v4 Announce Type: replace Abstract: High quality annotations are increasingly a bottleneck in the explosively growing machine learning ecosystem.

By Florian E. Dorner, Vivian Y. Nastl, Moritz Hardt

llms

arXiv Machine Learning

Jun 2

Provable Data Scaling Law for Meta Learning via Complexity Minimization

arXiv:2606. 02008v1 Announce Type: cross Abstract: Pre-training has become a fundamental paradigm in modern machine learning, with one of its key empirical benefits being reduced downstream sample complexity as the scale of pre-training data increases.

By Kazuto Fukuchi, Ryuichiro Hataya, Kota Matsui

arXiv Machine Learning

4d ago

UnlearningSoup: Is Repeated Tuning Necessary for Large Language Model Unlearning?

arXiv:2609.37076v1 Announce Type: new Abstract: Large language models trained on vast corpora inherently risk memorizing harmful content that may later re-emerge in their outputs. To mitigate this is...

By Puning Yang, Qizhou Wang, Junchi Yu, Bo Han, Xiuying Chen

llms

arXiv Machine Learning

Jul 22

How Benchmark Prediction from Fewer Data Misses the Mark

arXiv:2506. 07673v2 Announce Type: replace Abstract: Large language model (LLM) evaluation is increasingly costly, prompting interest in methods that speed up evaluation by shrinking benchmark datasets.

By Guanhua Zhang, Florian E. Dorner, Moritz Hardt

llms benchmarks

arXiv Machine Learning

Jul 7

CollabEval: Statistically Efficient Collaborative Model Evaluation via Matrix Completion

arXiv:2607. 05046v1 Announce Type: new Abstract: Evaluating generative AI models is a routine, but resource-intensive, process that is conducted over and over again during the course of model development.

By Adam Fisch, Daniel Deutsch, Joshua Maynez, Alekh Agarwal, Jonathan Berant, William Cohen, Amir Globerson, Jacob Eisenstein

efficiency benchmarks

One email a morning, machine-written

Related stories

Labeled-Data-Free Meta-Learning: Efficient Task Generation Using Pre-trained Models and Unlabeled Data

Limits to scalable evaluation at the frontier: LLM as Judge won't beat twice the data

Provable Data Scaling Law for Meta Learning via Complexity Minimization

UnlearningSoup: Is Repeated Tuning Necessary for Large Language Model Unlearning?

How Benchmark Prediction from Fewer Data Misses the Mark

CollabEval: Statistically Efficient Collaborative Model Evaluation via Matrix Completion