arXiv Machine Learning

You Don't Need to Run Every Eval

arXiv:2606. 24020v1 Announce Type: new Abstract: A modern model release reports scores on 40+ benchmarks and the same evaluations were run many more times before it: to track training progress, compare design choices, and select the checkpoint for the release.

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

arXiv AI

Jul 14

Coresets Before Score Sets: Evaluation-Unsupervised Prompt Subset Selection for LLM Benchmarks

arXiv:2607. 09739v1 Announce Type: new Abstract: We study LLM benchmark coreset selection: selecting a small subset of prompts over multiple benchmarks whose induced model scores and rankings approximate those obtained from the full benchmark suite.

By Jihan Yao, Gantavya Bhatt, Arnav Das, Peter Jin, Ke Bao, Qiaolin Yu, Khushi Bhardwaj, Chang Su, Jialei Wang, Yikai Zhu, Sugam Devare, Damon Mosk-Aoyama, Zhen Dong, Venkat Krishna Srinivasan, Yineng Zhang, Oleksii Kuchaiev, Jiantao Jiao, Banghua Zhu, Jeff Bilmes

llms rag benchmarks

arXiv AI

2d ago

Don't Claim Benchmark-Oriented Optimization Improves General Coding Capability -- Diverse Evaluation Is Required

arXiv:2608. 13566v1 Announce Type: cross Abstract: Post-training papers, model cards, and blog posts often treat scores on a small set of coding benchmarks (e.

By Egor Shibaev, Vera Kudrevskaia, Timur Galimzyanov, Mikhail Evtikhiev, Ana Terna, Rastislav Rabatin, Timur Kudashev, Timofey Bryksin, Arina Puchkova, Patrik Bartak, Egor Bogomolov, Sergey Titov

llms agents fine-tuning benchmarks

arXiv AI

Jul 7

Incompressible Knowledge Probes: Estimating Black-Box LLM Parameter Counts via Factual Capacity

arXiv:2604. 24827v2 Announce Type: replace-cross Abstract: Closed-source frontier labs do not disclose parameter counts.

By Bojie Li

llms benchmarks safety

arXiv AI

Jul 3

PACE: A Proxy for Agentic Capability Evaluation

arXiv:2607. 02032v1 Announce Type: new Abstract: Evaluating LLM agents on benchmarks like SWE-Bench and GAIA can be expensive, time-consuming, and requires complex infrastructure.

By Yueqi Song, Lintang Sutawika, Jiarui Liu, Lindia Tjuatja, Jiayi Geng, Yunze Xiao, Daniel Lee, Aditya Bharat Soni, Vincent Lo, Xiang Yue, Graham Neubig

llms agents benchmarks

arXiv AI

Aug 6

What We Observe as LLM Behavior Can Be a Side-effect of Inference Backend

arXiv:2608. 04714v1 Announce Type: cross Abstract: Benchmark scores are reported as properties of a model, yet the inference framework used to produce them, such as HuggingFace, vLLM, or Ollama, are considered non-influential and their names and versions are almost never disclosed.

By Shahed Masoudian, Passant Shafaei, Monorama Swain, Markus Schedl

llms benchmarks safety

arXiv AI

Jul 29

GAUGE: Grading Agent-Built Financial Models Without a Golden Answer

arXiv:2607. 24889v1 Announce Type: cross Abstract: Financial models combine public disclosures with analyst assumptions to produce forecasts and valuations.

By Jiacheng Lu, Sinuo Wang, Wentao Zhao, Rui Sun, Cheng Hua, Tao Song, Hui Cai, Beidi Luan, Zhengze Wu, Lingjing Teng, Yijia He, Jing Li, Daxin Jiang, Zuo Bai, Haibing Guan

agents benchmarks

arXiv Machine Learning

Jul 10

Stop Guessing When to Stop Testing: Efficient Model Evaluation with Just Enough Data

arXiv:2607. 08522v1 Announce Type: new Abstract: The inherent rigidity of fixed-size benchmarks makes them an inefficient tool for model evaluation.

By Ofir Arviv, Kristjan Greenewald, Yotam Perlitz, Hadar Mulian, Michal Shmueli-Scheuer, Leshem Choshen

multimodal benchmarks

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 AI

Jun 29

When Is an LLM Worth It for Hyperparameter Optimization? A Budget-Matched Study on Tabular Data Finds the Warm-Start Is a Default Configuration, Not the Model

arXiv:2606. 21641v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have been proposed as hyperparameter-optimization (HPO) advisors that "warm-start" search from prior knowledge, proposing strong configurations in very few evaluations.

By Carson Rodrigues, Oysturn Vas, Isaiah Abner DCosta, Nithish Kumar Prabhakaran

llms benchmarks

arXiv AI

Jun 17

TuneAhead: Predicting Fine-tuning Performance Before Full Training Begins

arXiv:2606. 17660v1 Announce Type: cross Abstract: Fine-tuning large language models (LLMs) is compute-intensive and error-prone: model performance depends sensitively on data quality and hyperparameter choices, and na\"ive runs can even degrade model performance.

By Yuxiang Luo, Haonan Long, Chen Wang, Qiqi Duan, Xiaotian Lin, Yanwei Xu, Yuyu Luo, Weikai Yang, Nan Tang

llms fine-tuning data-engineering

arXiv AI

Aug 10

Winning by Peeking: Unenforced Budgets and Test-Set Selection Inflate Short-Budget AutoML Comparisons

arXiv:2608. 07303v1 Announce Type: new Abstract: Comparisons between AutoML systems at short time budgets -- tens of seconds rather than hours -- are common in tool READMEs and workshop papers, and they are easy to get wrong.

By Guilin Zhang, Kai Zhao

safety

Related stories