English
Related papers

Related papers: When Benchmarks Leak: Inference-Time Decontaminati…

200 papers

The rapid evolution of Large Language Model (LLM) inference systems has yielded significant efficiency improvements. However, our systematic analysis reveals that current evaluation methodologies frequently exhibit fundamental flaws, often…

Natural Language Processing (NLP) research is increasingly focusing on the use of Large Language Models (LLMs), with some of the most popular ones being either fully or partially closed-source. The lack of access to model details,…

Computation and Language · Computer Science 2024-02-23 Simone Balloccu , Patrícia Schmidtová , Mateusz Lango , Ondřej Dušek

Modern Large Language Models (LLMs) have shown astounding capabilities of code understanding and synthesis. In order to assess such capabilities, several benchmarks have been devised (e.g., HumanEval). However, most benchmarks focus on code…

Software Engineering · Computer Science 2025-03-07 Julian Aron Prenner , Romain Robbes

Large Language Models (LLMs) applied to code-related applications have emerged as a prominent field, attracting significant interest from both academia and industry. However, as new and improved LLMs are developed, existing evaluation…

Software Engineering · Computer Science 2024-06-07 Naman Jain , King Han , Alex Gu , Wen-Ding Li , Fanjia Yan , Tianjun Zhang , Sida Wang , Armando Solar-Lezama , Koushik Sen , Ion Stoica

Robust benchmarks are crucial for evaluating Multimodal Large Language Models (MLLMs). Yet we find that models can ace many multimodal benchmarks without strong visual understanding, instead exploiting biases, linguistic priors, and…

Computer Vision and Pattern Recognition · Computer Science 2025-11-07 Ellis Brown , Jihan Yang , Shusheng Yang , Rob Fergus , Saining Xie

The evaluation of large language models (LLMs) relies heavily on standardized benchmarks. These benchmarks provide useful aggregated metrics for a given capability, but those aggregated metrics can obscure (i) particular sub-areas where the…

Computation and Language · Computer Science 2025-12-25 Matyas Bohacek , Nino Scherrer , Nicholas Dufour , Thomas Leung , Christoph Bregler , Stephanie C. Y. Chan

Benchmarks are central to measuring the capabilities of large language models and guiding model development, yet widespread data leakage from pretraining corpora undermines their validity. Models can match memorized content rather than…

Computation and Language · Computer Science 2025-10-10 Qin Liu , Jacob Dineen , Yuxi Huang , Sheng Zhang , Hoifung Poon , Ben Zhou , Muhao Chen

Deobfuscating JavaScript (JS) code poses a significant challenge in web security, particularly as obfuscation techniques are frequently used to conceal malicious activities within scripts. While Large Language Models (LLMs) have recently…

Cryptography and Security · Computer Science 2025-06-26 Guoqiang Chen , Xin Jin , Zhiqiang Lin

The safety and alignment of Large Language Models (LLMs) are critical for their responsible deployment. Current evaluation methods predominantly focus on identifying and preventing overtly harmful outputs. However, they often fail to…

This paper investigates the ability of large language models (LLMs) to recognise and solve tasks which have been obfuscated beyond recognition. Focusing on competitive programming and benchmark tasks (LeetCode and MATH), we compare…

Machine Learning · Computer Science 2025-05-30 Radzim Sendyka , Christian Cabrera , Andrei Paleyes , Diana Robinson , Neil Lawrence

If LLM training data is polluted with benchmark test data, then benchmark performance gives biased estimates of out-of-distribution (OOD) generalization. Typical decontamination filters use n-gram matching which fail to detect semantic…

Machine Learning · Computer Science 2026-02-16 Ari Spiesberger , Juan J. Vazquez , Nicky Pochinkov , Tomáš Gavenčiak , Peli Grietzer , Gavin Leech , Nandi Schoots

Large language models (LLMs) often appear to excel on public benchmarks, but these high scores may mask an overreliance on dataset-specific surface cues rather than true language understanding. We introduce the Chameleon Benchmark Overfit…

Computation and Language · Computer Science 2025-09-18 Nurit Cohen-Inger , Yehonatan Elisha , Bracha Shapira , Lior Rokach , Seffi Cohen

The emergence of large language models (LLMs) has sparked enormous interest due to their potential application across a range of educational tasks. For example, recent work in programming education has used LLMs to generate learning…

Software Engineering · Computer Science 2024-05-10 Charles Koutcheme , Nicola Dainese , Sami Sarsa , Juho Leinonen , Arto Hellas , Paul Denny

Benchmark-based evaluation, e.g., multiple-choice questions (MCQs) and open-ended questions (OEQs), is widely used for evaluating Large Language Models (LLMs), yet their reliability is undermined by benchmark contamination. When pre-exposed…

Computation and Language · Computer Science 2026-05-18 Yuyang Xu , Renjun Hu , Haochao Ying , Jian Wu , Xing Shi , Wei Lin

Recent research on large language models (LLMs) has demonstrated their ability to understand and employ deceptive behavior, even without explicit prompting. However, such behavior has only been observed in rare, specialized cases and has…

Computation and Language · Computer Science 2025-06-24 Laurène Vaugrante , Francesca Carlon , Maluna Menke , Thilo Hagendorff

Data contamination poses a significant challenge to the fairness of LLM evaluations in natural language processing tasks by inadvertently exposing models to test data during training. Current studies attempt to mitigate this issue by…

Computation and Language · Computer Science 2025-11-25 Jingqian Zhao , Bingbing Wang , Geng Tu , Yice Zhang , Qianlong Wang , Bin Liang , Jing Li , Ruifeng Xu

The rise of music large language models (LLMs) demands robust methods of evaluating output quality, especially in distinguishing high-quality compositions from "garbage music". Curiously, we observe that the standard cross-entropy loss -- a…

Sound · Computer Science 2026-02-04 Xiaosha Li , Chun Liu , Ziyu Wang

Large Language Models (LLMs) are known to hallucinate, whereby they generate plausible but inaccurate text. This phenomenon poses significant risks in critical applications, such as medicine or law, necessitating robust hallucination…

Computation and Language · Computer Science 2024-10-23 Benedict Aaron Tjandra , Muhammed Razzak , Jannik Kossen , Kunal Handa , Yarin Gal

Label noise is a common problem in real-world datasets, affecting both model training and validation. Clean data are essential for achieving strong performance and ensuring reliable evaluation. While various techniques have been proposed to…

Machine Learning · Computer Science 2025-10-21 Henrique Pickler , Jorge K. S. Kamassury , Danilo Silva

As large language models achieve increasingly impressive results, questions arise about whether such performance is from generalizability or mere data memorization. Thus, numerous data contamination detection methods have been proposed.…

Computation and Language · Computer Science 2024-12-10 Vinay Samuel , Yue Zhou , Henry Peng Zou
‹ Prev 1 4 5 6 7 8 10 Next ›