English
Related papers

Related papers: Proving Test Set Contamination in Black Box Langua…

200 papers

Large Language Models remain vulnerable to adversarial prompts that elicit toxic content even after safety alignment. We present ToxSearch, a black-box evolutionary framework that tests model safety by evolving prompts in a synchronous…

Neural and Evolutionary Computing · Computer Science 2026-01-27 Onkar Shelar , Travis Desell

Large Language Models face security threats from jailbreak attacks. Existing research has predominantly focused on prompt-level attacks while largely ignoring the underexplored attack surface of user-controlled response prefilling. This…

Cryptography and Security · Computer Science 2025-08-27 Yakai Li , Jiekang Hu , Weiduan Sang , Luping Ma , Dongsheng Nie , Weijuan Zhang , Aimin Yu , Yi Su , Qingjia Huang , Qihang Zhou

We show that large pre-trained language models are inherently highly capable of identifying label errors in natural language datasets: simply examining out-of-sample data points in descending order of fine-tuned task loss significantly…

Computation and Language · Computer Science 2022-12-16 Derek Chong , Jenny Hong , Christopher D. Manning

Automatic content moderation is crucial to ensuring safety in social media. Language Model-based classifiers are being increasingly adopted for this task, but it has been shown that they perpetuate racial and social biases. Even if several…

Computation and Language · Computer Science 2026-03-12 Alessandra Urbinati , Mirko Lai , Simona Frenda , Marco Antonio Stranisci

Neural network models have been very successful in natural language inference, with the best models reaching 90% accuracy in some benchmarks. However, the success of these models turns out to be largely benchmark specific. We show that…

Computation and Language · Computer Science 2019-06-04 Aarne Talman , Stergios Chatzikyriakidis

Evaluating language models fairly is increasingly difficult as static benchmarks risk contamination by training data, obscuring whether models truly reason or recall. We introduce BeyondBench, an evaluation framework using algorithmic…

Computation and Language · Computer Science 2026-03-06 Gaurav Srivastava , Aafiya Hussain , Zhenyu Bi , Swastik Roy , Priya Pitre , Meng Lu , Morteza Ziyadi , Xuan Wang

We are currently in an era of fierce competition among various large language models (LLMs) continuously pushing the boundaries of benchmark performance. However, genuinely assessing the capabilities of these LLMs has become a challenging…

Computation and Language · Computer Science 2024-06-04 Wenhong Zhu , Hongkun Hao , Zhiwei He , Yunze Song , Yumeng Zhang , Hanxu Hu , Yiran Wei , Rui Wang , Hongyuan Lu

Effective training of today's large language models (LLMs) depends on large batches and long sequences for throughput and accuracy. To handle variable-length sequences on hardware accelerators, it is common practice to introduce padding…

Computation and Language · Computer Science 2022-10-07 Mario Michael Krell , Matej Kosec , Sergio P. Perez , Andrew Fitzgibbon

In this paper, we show that knowledge distillation can be subverted to manipulate language model benchmark scores, revealing a critical vulnerability in current evaluation practices. We introduce "Data Laundering," a process that enables…

Computation and Language · Computer Science 2025-06-05 Jonibek Mansurov , Akhmed Sakip , Alham Fikri Aji

Large language models have demonstrated remarkable proficiency in long and complex reasoning tasks. However, they frequently exhibit a problematic reliance on familiar reasoning patterns, a phenomenon we term \textit{reasoning rigidity}.…

Artificial Intelligence · Computer Science 2025-05-26 Doohyuk Jang , Yoonjeon Kim , Chanjae Park , Hyun Ryu , Eunho Yang

Finetuning can significantly modify the behavior of large language models, including introducing harmful or unsafe behaviors. To study these risks, researchers develop model organisms: models finetuned to exhibit specific known behaviors…

Computation and Language · Computer Science 2026-05-05 Mohammed Abu Baker , Luca Baroni , Dan Wilhelm

Label noise in real-world datasets encodes wrong correlation patterns and impairs the generalization of deep neural networks (DNNs). It is critical to find efficient ways to detect corrupted patterns. Current methods primarily focus on…

Machine Learning · Computer Science 2022-06-22 Zhaowei Zhu , Zihao Dong , Yang Liu

The growing importance of massive datasets used for deep learning makes robustness to label noise a critical property for classifiers to have. Sources of label noise include automatic labeling, non-expert labeling, and label corruption by…

Machine Learning · Computer Science 2019-01-30 Dan Hendrycks , Mantas Mazeika , Duncan Wilson , Kevin Gimpel

The impressive capabilities of recent language models can be largely attributed to the multi-trillion token pretraining datasets that they are trained on. However, model developers fail to disclose their construction methodology which has…

Language models (LMs) can reproduce (or amplify) toxic language seen during training, which poses a risk to their practical application. In this paper, we conduct extensive experiments to study this phenomenon. We analyze the impact of…

Computation and Language · Computer Science 2022-03-08 Canwen Xu , Zexue He , Zhankui He , Julian McAuley

Large language models (LLMs) have demonstrated impressive reasoning abilities across a wide range of tasks, but data contamination undermines the objective evaluation of these capabilities. This problem is further exacerbated by malicious…

Machine Learning · Computer Science 2026-05-22 Yifan Lan , Yuanpu Cao , Hanyu Wang , Lu Lin , Jinghui Chen

The rapid development of Large Language Models (LLMs) like GPT-4, Claude-3, and Gemini has transformed the field of natural language processing. However, it has also resulted in a significant issue known as Benchmark Data Contamination…

Computation and Language · Computer Science 2024-06-07 Cheng Xu , Shuhao Guan , Derek Greene , M-Tahar Kechadi

Data contamination -- the accidental consumption of evaluation examples within the pre-training data -- can undermine the validity of evaluation benchmarks. In this paper, we present a rigorous analysis of the effects of contamination on…

Computation and Language · Computer Science 2025-02-03 Muhammed Yusuf Kocyigit , Eleftheria Briakou , Daniel Deutsch , Jiaming Luo , Colin Cherry , Markus Freitag

Recent work has shown that Large Language Models (LLMs) can unintentionally leak sensitive information present in their training data. In this paper, we present Model Perturbations (MoPe), a new method to identify with high confidence if a…

Machine Learning · Computer Science 2023-10-24 Marvin Li , Jason Wang , Jeffrey Wang , Seth Neel

We present two novel unsupervised methods for eliminating toxicity in text. Our first method combines two recent ideas: (1) guidance of the generation process with small style-conditional language models and (2) use of paraphrasing models…

Computation and Language · Computer Science 2021-11-04 David Dale , Anton Voronov , Daryna Dementieva , Varvara Logacheva , Olga Kozlova , Nikita Semenov , Alexander Panchenko
‹ Prev 1 4 5 6 7 8 10 Next ›