English
Related papers

Related papers: LogProber: Disentangling confidence from contamina…

200 papers

Large language models (LM) generate remarkably fluent text and can be efficiently adapted across NLP tasks. Measuring and guaranteeing the quality of generated text in terms of safety is imperative for deploying LMs in the real world; to…

Peer review is crucial for advancing and improving science through constructive criticism. However, toxic feedback can discourage authors and hinder scientific progress. This work explores an important but underexplored area: detecting…

Computation and Language · Computer Science 2025-02-05 Man Luo , Bradley Peterson , Rafael Gan , Hari Ramalingame , Navya Gangrade , Ariadne Dimarogona , Imon Banerjee , Phillip Howard

Data contamination in model evaluation has become increasingly prevalent with the growing popularity of large language models. It allows models to "cheat" via memorisation instead of displaying true capabilities. Therefore, contamination…

Computation and Language · Computer Science 2024-01-30 Yucheng Li , Frank Guerin , Chenghua Lin

Toxicity detection is crucial for maintaining the peace of the society. While existing methods perform well on normal toxic contents or those generated by specific perturbation methods, they are vulnerable to evolving perturbation patterns.…

Cryptography and Security · Computer Science 2025-03-05 Hankun Kang , Jianhao Chen , Yongqi Li , Xin Miao , Mayi Xu , Ming Zhong , Yuanyuan Zhu , Tieyun Qian

With the advent of larger and more complex deep learning models, such as in Natural Language Processing (NLP), model qualities like explainability and interpretability, albeit highly desirable, are becoming harder challenges to tackle and…

Computation and Language · Computer Science 2024-01-30 Amrita Bhattacharjee , Raha Moraffah , Joshua Garland , Huan Liu

Training data is a critical and often proprietary asset in Large Language Model (LLM) development, motivating the use of data watermarking to embed model-transferable signals for usage verification. We identify low coverage as a vital yet…

Cryptography and Security · Computer Science 2026-04-30 Hengyu Wu , Yang Cao

Backdoor attacks pose severe security threats to large language models (LLMs), where a model behaves normally under benign inputs but produces malicious outputs when a hidden trigger appears. Existing backdoor removal methods typically…

Cryptography and Security · Computer Science 2026-03-17 Jianwei Li , Jung-Eun Kim

The increasing fluency and widespread usage of large language models (LLMs) highlight the desirability of corresponding tools aiding detection of LLM-generated text. In this paper, we identify a property of the structure of an LLM's…

Computation and Language · Computer Science 2023-07-25 Eric Mitchell , Yoonho Lee , Alexander Khazatsky , Christopher D. Manning , Chelsea Finn

Open benchmarks are essential for evaluating and advancing large language models, offering reproducibility and transparency. However, their accessibility makes them likely targets of test set contamination. In this work, we introduce…

Computation and Language · Computer Science 2025-09-25 Yize Cheng , Wenxiao Wang , Mazda Moayeri , Soheil Feizi

Benchmark datasets are critical for reproducible, reliable, and discriminative evaluation of LLMs. However, recent studies reveal that many benchmark datasets are included in pretraining corpora, i.e., $\textit{contaminated}$, which…

Machine Learning · Computer Science 2026-05-20 Ali Al-Lawati , Jason Lucas , Dongwon Lee , Suhang Wang

Detecting machine-generated text is essential for transparency and accountability when deploying large language models (LLMs). Among detection approaches, watermarking is a statistically reliable method by design -- it embeds detectable…

Computation and Language · Computer Science 2026-05-05 Koshiro Saito , Ryuto Koike , Masahiro Kaneko , Naoaki Okazaki

Large Language Models (LLMs) as judges and LLM-based data synthesis have emerged as two fundamental LLM-driven data annotation methods in model development. While their combination significantly enhances the efficiency of model training and…

Machine Learning · Computer Science 2026-03-05 Dawei Li , Renliang Sun , Yue Huang , Ming Zhong , Bohan Jiang , Jiawei Han , Xiangliang Zhang , Wei Wang , Huan Liu

Since the proliferation of LLMs, there have been concerns about their misuse for harmful content creation and spreading. Recent studies justify such fears, providing evidence of LLM vulnerabilities and high potential of their misuse. Humans…

Computation and Language · Computer Science 2025-03-20 Dominik Macko , Robert Moro , Ivan Srba

This paper considers the problem of estimating the information leakage of a system in the black-box scenario. It is assumed that the system's internals are unknown to the learner, or anyway too complicated to analyze, and the only available…

Cryptography and Security · Computer Science 2021-11-29 Marco Romanelli , Konstantinos Chatzikokolakis , Catuscia Palamidessi , Pablo Piantanida

With the development of large language models (LLMs), detecting whether text is generated by a machine becomes increasingly challenging in the face of malicious use cases like the spread of false information, protection of intellectual…

Computation and Language · Computer Science 2024-04-03 Ying Zhou , Ben He , Le Sun

Toxic content detection is crucial for online services to remove inappropriate content that violates community standards. To automate the detection process, prior works have proposed varieties of machine learning (ML) approaches to train…

Computation and Language · Computer Science 2023-12-14 Jiang Zhang , Qiong Wu , Yiming Xu , Cheng Cao , Zheng Du , Konstantinos Psounis

As large language models (LLMs) become increasingly prevalent in global applications, ensuring that they are toxicity-free across diverse linguistic contexts remains a critical challenge. We explore "Cross-lingual Detoxification", a…

Computation and Language · Computer Science 2025-10-24 Himanshu Beniwal , Youngwoo Kim , Maarten Sap , Soham Dan , Thomas Hartvigsen

Benchmarking is the de-facto standard for evaluating LLMs, due to its speed, replicability and low cost. However, recent work has pointed out that the majority of the open source benchmarks available today have been contaminated or leaked…

Cryptography and Security · Computer Science 2024-06-25 Tanmay Rajore , Nishanth Chandran , Sunayana Sitaram , Divya Gupta , Rahul Sharma , Kashish Mittal , Manohar Swaminathan

Large Language Models (LLMs) are often provided as a service via an API, making it challenging for developers to detect changes in their behavior. We present an approach to monitor LLMs for changes by comparing the distributions of…

Computation and Language · Computer Science 2025-04-18 Alden Dima , James Foulds , Shimei Pan , Philip Feldman

Verifying the provenance of content is crucial to the functioning of many organizations, e.g., educational institutions, social media platforms, and firms. This problem is becoming increasingly challenging as text generated by Large…

Machine Learning · Statistics 2026-03-24 Tara Radvand , Mojtaba Abdolmaleki , Mohamed Mostagir , Ambuj Tewari