English
Related papers

Related papers: LLM Olympiad: Why Model Evaluation Needs a Sealed …

200 papers

In Machine Learning, a benchmark refers to an ensemble of datasets associated with one or multiple metrics together with a way to aggregate different systems performances. They are instrumental in (i) assessing the progress of new methods…

Computation and Language · Computer Science 2022-10-10 Pierre Colombo , Nathan Noiry , Ekhine Irurozki , Stephan Clemencon

Reliable evaluation protocols are of utmost importance for reproducible NLP research. In this work, we show that sometimes neither metric nor conventional human evaluation is sufficient to draw conclusions about system performance. Using…

Computation and Language · Computer Science 2021-01-25 Yevgeniy Puzikov

Progress in AI is often demonstrated by new models claiming improved performance on tasks measuring model capabilities. Evaluating language models can be particularly challenging, as choices of how a model is evaluated on a task can lead to…

Computation and Language · Computer Science 2025-02-12 Yuling Gu , Oyvind Tafjord , Bailey Kuehl , Dany Haddad , Jesse Dodge , Hannaneh Hajishirzi

Large Language Models (LLMs) are commonly evaluated using human-crafted benchmarks, under the premise that higher scores implicitly reflect stronger human-like performance. However, there is growing concern that LLMs may ``game" these…

Computation and Language · Computer Science 2024-12-16 Zhikai Lei , Tianyi Liang , Hanglei Hu , Jin Zhang , Yunhua Zhou , Yunfan Shao , Linyang Li , Chenchui Li , Changbo Wang , Hang Yan , Qipeng Guo

Large language models (LLMs) are becoming increasingly capable mathematical collaborators, but static benchmarks are no longer sufficient for evaluating progress: they are often narrow in scope, quickly saturated, and rarely updated. This…

Computation and Language · Computer Science 2026-05-18 Jasper Dekoninck , Nikola Jovanović , Tim Gehrunger , Kári Rögnvaldsson , Ivo Petrov , Chenhao Sun , Martin Vechev

Competitive programming has emerged as a critical benchmark for evaluating the reasoning and coding capabilities of Large Language Models (LLMs). Despite impressive progress on existing benchmarks, we argue that current evaluations…

Current Large Language Models (LLMs) benchmarks are often based on open-ended or close-ended QA evaluations, avoiding the requirement of human labor. Close-ended measurements evaluate the factuality of responses but lack expressiveness.…

The performance of large language models (LLMs) continues to improve, as reflected in rising scores on standard benchmarks. However, the lack of transparency around training data raises concerns about potential overlap with evaluation sets…

Computation and Language · Computer Science 2025-06-02 Naila Shafirni Hidayat , Muhammad Dehan Al Kautsar , Alfan Farizki Wicaksono , Fajri Koto

Benchmark-based evaluation is the de facto standard for comparing large language models (LLMs). However, its reliability is increasingly threatened by test set contamination, where test samples or their close variants leak into training…

Computation and Language · Computer Science 2026-01-28 Jianzhe Chai , Yu Zhe , Jun Sakuma

Although large language models (LLMs) have shown exceptional capabilities across a wide range of tasks, reliable evaluation remains a critical challenge due to data contamination, opaque operation, and subjective preferences. To address…

Artificial Intelligence · Computer Science 2026-04-15 Qianhong Guo , Wei Xie , Xiaofang Cai , Enze Wang , Shuoyoucheng Ma , Xiaobing Sun , Tian Xia , Kai Chen , Xiaofeng Wang , Baosheng Wang

Large Language Models (LLMs) are increasingly used to simulate public opinion and other social phenomena. Most current studies constrain these simulations to multiple-choice or short-answer formats for ease of scoring and comparison, but…

Computation and Language · Computer Science 2026-03-17 Bolei Ma , Yong Cao , Indira Sen , Anna-Carolina Haensch , Frauke Kreuter , Barbara Plank , Daniel Hershcovich

Large Language Models (LLMs) are increasingly vulnerable to a sophisticated form of adversarial prompting known as camouflaged jailbreaking. This method embeds malicious intent within seemingly benign language to evade existing safety…

Cryptography and Security · Computer Science 2025-09-09 Youjia Zheng , Mohammad Zandsalimy , Shanu Sushmita

Modern language models (LMs) pose a new challenge in capability assessment. Static benchmarks inevitably saturate without providing confidence in the deployment tolerances of LM-based systems, but developers nonetheless claim that their…

Software Engineering · Computer Science 2024-07-31 Michael Saxon , Ari Holtzman , Peter West , William Yang Wang , Naomi Saphra

When deploying large language models (LLMs), it is important to ensure that these models are not only capable, but also reliable. Many benchmarks have been created to track LLMs' growing capabilities, however there has been no similar focus…

Machine Learning · Computer Science 2025-02-06 Joshua Vendrow , Edward Vendrow , Sara Beery , Aleksander Madry

Recent observations have underscored a disparity between the inflated benchmark scores and the actual performance of LLMs, raising concerns about potential contamination of evaluation benchmarks. This issue is especially critical for…

Computation and Language · Computer Science 2024-04-05 Chunyuan Deng , Yilun Zhao , Xiangru Tang , Mark Gerstein , Arman Cohan

Current evaluations of large language models (LLMs) rely on benchmark scores, but it is difficult to interpret what these individual scores reveal about a model's overall skills. Specifically, as a community we lack understanding of how…

Computation and Language · Computer Science 2025-07-29 Aviya Maimon , Amir DN Cohen , Gal Vishne , Shauli Ravfogel , Reut Tsarfaty

The rapid development of large language models (LLMs) has necessitated the creation of benchmarks to evaluate their performance. These benchmarks resemble human tests and surveys, as they consist of sets of questions designed to measure…

Computation and Language · Computer Science 2025-01-30 Denis Federiakin

Large language models (LLMs) are powerful tools capable of handling diverse tasks. Comparing and selecting appropriate LLMs for specific tasks requires systematic evaluation methods, as models exhibit varying capabilities across different…

Computation and Language · Computer Science 2025-06-04 Anna Sokol , Elizabeth Daly , Michael Hind , David Piorkowski , Xiangliang Zhang , Nuno Moniz , Nitesh Chawla

As Large Language Models (LLMs) advance, their potential for widespread societal impact grows simultaneously. Hence, rigorous LLM evaluations are both a technical necessity and social imperative. While numerous evaluation benchmarks have…

Computation and Language · Computer Science 2025-04-22 Jaime Raldua Veuthey , Zainab Ali Majid , Suhas Hariharan , Jacob Haimes

Humans do not just find mistakes after the fact -- we often catch them mid-stream because 'reflection' is tied to the goal and its constraints. Today's large language models produce reasoning tokens and 'reflective' text, but is it…

Artificial Intelligence · Computer Science 2025-10-24 Sion Weatherhead , Flora Salim , Aaron Belbasis