English
Related papers

Related papers: ReCaLL: Membership Inference via Relative Conditio…

200 papers

Generating rational and generally accurate responses to tasks, often accompanied by example demonstrations, highlights Large Language Model's (LLM's) remarkable In-Context Learning (ICL) capabilities without requiring updates to the model's…

Machine Learning · Computer Science 2025-06-17 Debanjan Dutta , Faizanuddin Ansari , Swagatam Das

Recent claims of strong performance by Large Language Models (LLMs) on causal discovery are undermined by a key flaw: many evaluations rely on benchmarks likely included in pretraining corpora. Thus, apparent success suggests that LLM-only…

We unveil that internal representations in large language models (LLMs) serve as reliable proxies of learned knowledge, and propose RECALL, a novel representation-aware model merging framework for continual learning without access to…

Computation and Language · Computer Science 2025-10-24 Bowen Wang , Haiyuan Wan , Liwen Shi , Chen Yang , Peng He , Yue Ma , Haochen Han , Wenhao Li , Tiao Tan , Yongjian Li , Fangming Liu , Yifan Gong , Sheng Zhang

Learning from self-sampled data and sparse environmental feedback remains a fundamental challenge in training self-evolving agents. Temporal credit assignment mitigates this issue by transforming sparse feedback into dense supervision…

Machine Learning · Computer Science 2026-02-20 Wen-Tse Chen , Jiayu Chen , Fahim Tajwar , Hao Zhu , Xintong Duan , Ruslan Salakhutdinov , Jeff Schneider

This study reveals a previously unexplored vulnerability in the safety alignment of Large Language Models (LLMs). Existing aligned LLMs predominantly respond to unsafe queries with refusals, which often begin with a fixed set of prefixes…

Cryptography and Security · Computer Science 2026-01-28 Yangyang Guo , Ziwei Xu , Si Liu , Zhiming Zheng , Mohan Kankanhalli

Large Language Models (LLMs) have demonstrated an impressive capability known as In-context Learning (ICL), which enables them to acquire knowledge from textual demonstrations without the need for parameter updates. However, many studies…

Computation and Language · Computer Science 2024-06-04 Yi Su , Yunpeng Tai , Yixin Ji , Juntao Li , Bowen Yan , Min Zhang

Retrieval-Augmented Generation (RAG) and Supervised Finetuning (SFT) have become the predominant paradigms for equipping Large Language Models (LLMs) with external knowledge for diverse, knowledge-intensive tasks. However, while such…

Cryptography and Security · Computer Science 2025-12-04 Haowei Fu , Bo Ni , Han Xu , Kunpeng Liu , Dan Lin , Tyler Derr

With large language models (LLMs) achieving remarkable breakthroughs in natural language processing (NLP) domains, LLM-enhanced recommender systems have received much attention and have been actively explored currently. In this paper, we…

Information Retrieval · Computer Science 2024-07-02 Jianghao Lin , Rong Shan , Chenxu Zhu , Kounianhua Du , Bo Chen , Shigang Quan , Ruiming Tang , Yong Yu , Weinan Zhang

Federated large language models (FedLLMs) enable cross-silo collaborative training among institutions while preserving data locality, making them appealing for privacy-sensitive domains such as law, finance, and healthcare. However, the…

Computation and Language · Computer Science 2026-02-26 Yingqi Hu , Zhuo Zhang , Jingyuan Zhang , Jinghua Wang , Qifan Wang , Lizhen Qu , Zenglin Xu

Hallucination in large language models (LLMs) is a fundamental challenge, particularly in open-domain question answering. Prior work attempts to detect hallucination with model-internal signals such as token-level entropy or generation…

Computation and Language · Computer Science 2025-11-25 Shuo Zhang , Fabrizio Gotti , Fengran Mo , Jian-Yun Nie

Large Language Models (LLMs) embed sensitive, human-generated data, prompting the need for unlearning methods. Although certified unlearning offers strong privacy guarantees, its restrictive assumptions make it unsuitable for LLMs, giving…

Machine Learning · Computer Science 2025-06-03 Rongzhe Wei , Mufei Li , Mohsen Ghassemi , Eleonora Kreačić , Yifan Li , Xiang Yue , Bo Li , Vamsi K. Potluru , Pan Li , Eli Chien

Deep Neural Network (DNN) models have been shown to have high empirical privacy leakages. Clinical language models (CLMs) trained on clinical data have been used to improve performance in biomedical natural language processing tasks. In…

Computation and Language · Computer Science 2021-04-20 Abhyuday Jagannatha , Bhanu Pratap Singh Rawat , Hong Yu

Membership inference attacks (MIAs) aim to infer whether a data point has been used to train a machine learning model. These attacks can be employed to identify potential privacy vulnerabilities and detect unauthorized use of personal data.…

Machine Learning · Computer Science 2023-10-03 Myeongseob Ko , Ming Jin , Chenguang Wang , Ruoxi Jia

With the improving semantic understanding capability of Large Language Models (LLMs), they exhibit a greater awareness and alignment with human values, but this comes at the cost of transparency. Although promising results are achieved via…

Computation and Language · Computer Science 2026-05-27 Nafis Tanveer Islam , Zhiming Zhao

Today, the training of large language models (LLMs) can involve personally identifiable information and copyrighted material, incurring dataset misuse. To mitigate the problem of dataset misuse, this paper explores \textit{dataset…

Cryptography and Security · Computer Science 2025-12-09 Ruikai Zhou , Kang Yang , Xun Chen , Wendy Hui Wang , Guanhong Tao , Jun Xu

Vision-language models (VLMs) are trained on large-scale image-text corpora that may contain private, copyrighted, or otherwise sensitive data, motivating membership inference as a tool for training-data auditing. This is especially…

Computer Vision and Pattern Recognition · Computer Science 2026-05-14 Hongyi Tang , Zhihao Zhu , Yi Yang

We introduce context augmentation, a data-augmentation approach that uses large language models (LLMs) to generate contexts around observed strings as a means of facilitating valid frequentist inference. These generated contexts serve to…

Methodology · Statistics 2025-07-01 Marc Ratkovic

A membership inference attack allows an adversary to query a trained machine learning model to predict whether or not a particular example was contained in the model's training dataset. These attacks are currently evaluated using…

Cryptography and Security · Computer Science 2022-04-13 Nicholas Carlini , Steve Chien , Milad Nasr , Shuang Song , Andreas Terzis , Florian Tramer

Given how large parts of publicly available text are crawled to pretrain large language models (LLMs), data creators increasingly worry about the inclusion of their proprietary data for model training without attribution or licensing. Their…

Machine Learning · Computer Science 2025-06-10 Saksham Rastogi , Pratyush Maini , Danish Pruthi

In very recent years more attention has been placed on probing the role of pre-training data in Large Language Models (LLMs) downstream behaviour. Despite the importance, there is no public tool that supports such analysis of pre-training…

Computation and Language · Computer Science 2023-03-28 Thuy-Trang Vu , Xuanli He , Gholamreza Haffari , Ehsan Shareghi