English
Related papers

Related papers: Data Contamination Calibration for Black-box LLMs

200 papers

Membership Inference Attacks (MIA) aim to infer whether a target data record has been utilized for model training or not. Existing MIAs designed for large language models (LLMs) can be bifurcated into two types: reference-free and…

Computation and Language · Computer Science 2024-11-27 Wenjie Fu , Huandong Wang , Chen Gao , Guanghua Liu , Yong Li , Tao Jiang

Large language models are trained on vast amounts of internet data, prompting concerns and speculation that they have memorized public benchmarks. Going from speculation to proof of contamination is challenging, as the pretraining data used…

Computation and Language · Computer Science 2023-11-27 Yonatan Oren , Nicole Meister , Niladri Chatterji , Faisal Ladhak , Tatsunori B. Hashimoto

The pretraining and fine-tuning approach has become the leading technique for various NLP applications. However, recent studies reveal that fine-tuning data, due to their sensitive nature, domain-specific characteristics, and…

Computation and Language · Computer Science 2024-11-13 Qian Sun , Hanpeng Wu , Xi Sheryl Zhang

The rise of Large Language Models (LLMs) has triggered legal and ethical concerns, especially regarding the unauthorized use of copyrighted materials in their training datasets. This has led to lawsuits against tech companies accused of…

Cryptography and Security · Computer Science 2025-01-17 Cédric Eichler , Nathan Champeil , Nicolas Anciaux , Alexandra Bensamoun , Heber Hwang Arcolezi , José Maria De Fuentes

Large Language models (LLMs) can generate complicated source code from natural language prompts. However, LLMs can generate output that deviates from what the user wants, requiring supervision and editing. To support this process, we offer…

Software Engineering · Computer Science 2026-01-01 David Gros , Prem Devanbu

Modern machine learning models are increasingly deployed behind APIs. This renders standard weight-privatization methods (e.g. DP-SGD) unnecessarily noisy at the cost of utility. While model weights may vary significantly across training…

Machine Learning · Computer Science 2026-01-21 Xiaochen Zhu , Mayuri Sridhar , Srinivas Devadas

As API access becomes a primary interface to large language models (LLMs), users often interact with black-box systems that offer little transparency into the deployed model. To reduce costs or maliciously alter model behaviors, API…

Cryptography and Security · Computer Science 2026-04-10 Xiaoyuan Zhu , Yaowen Ye , Tianyi Qiu , Hanlin Zhu , Sijun Tan , Ajraf Mannan , Jonathan Michala , Raluca Ada Popa , Willie Neiswanger

Data containing personal information is increasingly used to train, fine-tune, or query Large Language Models (LLMs). Text is typically scrubbed of identifying information prior to use, often with tools such as Microsoft's Presidio or…

Computation and Language · Computer Science 2026-02-16 Nataša Krčo , Zexi Yao , Matthieu Meeus , Yves-Alexandre de Montjoye

Training a machine learning model with data following a meaningful order, i.e., from easy to hard, has been proven to be effective in accelerating the training process and achieving better model performance. The key enabling technique is…

Cryptography and Security · Computer Science 2023-10-17 Joann Qiongna Chen , Xinlei He , Zheng Li , Yang Zhang , Zhou Li

Since machine learning model is often trained on a limited data set, the model is trained multiple times on the same data sample, which causes the model to memorize most of the training set data. Membership Inference Attacks (MIAs) exploit…

Machine Learning · Computer Science 2024-11-19 Depeng Chen , Xiao Liu , Jie Cui , Hong Zhong

Preference learning is a central component for aligning current LLMs, but this process can be vulnerable to data poisoning attacks. To address this concern, we introduce PoisonBench, a benchmark for evaluating large language models'…

Cryptography and Security · Computer Science 2025-06-09 Tingchen Fu , Mrinank Sharma , Philip Torr , Shay B. Cohen , David Krueger , Fazl Barez

Machine unlearning offers effective solutions for revoking the influence of specific training data on pre-trained model parameters. While existing approaches address unlearning for classification and generative models, they overlook an…

Machine Learning · Computer Science 2025-08-19 Yihan Wang , Yiwei Lu , Guojun Zhang , Franziska Boenisch , Adam Dziedzic , Yaoliang Yu , Xiao-Shan Gao

Inductive Conformal Prediction (ICP) provides a practical and effective approach for equipping deep learning models with uncertainty estimates in the form of set-valued predictions which are guaranteed to contain the ground truth with high…

Machine Learning · Computer Science 2023-12-11 Apoorva Sharma , Sushant Veer , Asher Hancock , Heng Yang , Marco Pavone , Anirudha Majumdar

Large language models (LLMs) have achieved remarkable success across many applications, but their ability to generate harmful content raises serious safety concerns. Although safety alignment techniques are often applied during pre-training…

Machine Learning · Computer Science 2026-04-24 Chengcan Wu , Zhixin Zhang , Zeming Wei , Yihao Zhang , Xiaokun Luan , Meng Sun

Ensuring safety alignment is a critical requirement for large language models (LLMs), particularly given increasing deployment in real-world applications. Despite considerable advancements, LLMs remain susceptible to jailbreak attacks,…

Cryptography and Security · Computer Science 2025-06-02 Xin Yi , Yue Li , Dongsheng Shi , Linlin Wang , Xiaoling Wang , Liang He

Large Language Models (LLMs) have the promise to revolutionize computing broadly, but their complexity and extensive training data also expose significant privacy vulnerabilities. One of the simplest privacy risks associated with LLMs is…

Machine Learning · Computer Science 2024-09-25 Rongting Zhang , Martin Bertran , Aaron Roth

In contrast to the standard learning paradigm where all classes can be observed in training data, learning with augmented classes (LAC) tackles the problem where augmented classes unobserved in the training data may emerge in the test…

Machine Learning · Computer Science 2023-06-13 Senlin Shu , Shuo He , Haobo Wang , Hongxin Wei , Tao Xiang , Lei Feng

Through in-context learning (ICL), large-scale language models are effective few-shot learners without additional model fine-tuning. However, the ICL performance does not scale well with the number of available training samples as it is…

Computation and Language · Computer Science 2023-06-16 Hyunsoo Cho , Hyuhng Joon Kim , Junyeob Kim , Sang-Woo Lee , Sang-goo Lee , Kang Min Yoo , Taeuk Kim

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

Large language models are increasingly trained on all the data ever produced by humans. Many have raised concerns about the trustworthiness of public benchmarks due to potential contamination in pre-training or fine-tuning datasets. While…

Computation and Language · Computer Science 2023-11-14 Shuo Yang , Wei-Lin Chiang , Lianmin Zheng , Joseph E. Gonzalez , Ion Stoica
‹ Prev 1 3 4 5 6 7 10 Next ›