English
Related papers

Related papers: Learning to Detect Language Model Training Data vi…

200 papers

Large language models (LLMs) often struggle with knowledge intensive NLP tasks, such as answering "Who won the latest World Cup?" because the knowledge they learn during training may be insufficient or outdated. Conditioning generation on…

Computation and Language · Computer Science 2025-03-04 Matthew Finlayson , Ilia Kulikov , Daniel M. Bikel , Barlas Oguz , Xilun Chen , Aasish Pappu

The effectiveness of Reinforcement Learning (RL) in Large Language Models (LLMs) depends on the nature and diversity of the data used before and during RL. In particular, reasoning problems can often be approached in multiple ways that rely…

Artificial Intelligence · Computer Science 2026-05-12 Aswin RRV , Jacob Dineen , Divij Handa , Mihir Parmar , Ben Zhou , Swaroop Mishra , Chitta Baral

Membership inference attacks (MIAs) are popular methods for empirically assessing the leakage of sensitive information in the training data through models or statistics learned from the data. The MIA vulnerability is often evaluated through…

Machine Learning · Computer Science 2026-05-26 Joonas Jälkö , Gauri Pradhan , Ossi Räisä , Antti Honkela

It is well-established that many iterative sparse reconstruction algorithms can be unrolled to yield a learnable neural network for improved empirical performance. A prime example is learned ISTA (LISTA) where weights, step sizes and…

Machine Learning · Computer Science 2020-10-06 Freya Behrens , Jonathan Sauder , Peter Jung

Multi-turn intent classification is notably challenging due to the complexity and evolving nature of conversational contexts. This paper introduces LARA, a Linguistic-Adaptive Retrieval-Augmentation framework to enhance accuracy in…

Computation and Language · Computer Science 2024-10-15 Junhua Liu , Yong Keat Tan , Bin Fu , Kwan Hui Lim

In a membership inference attack (MIA), an attacker exploits the overconfidence exhibited by typical machine learning models to determine whether a specific data point was used to train a target model. In this paper, we analyze the…

Information Theory · Computer Science 2025-06-10 Meiyi Zhu , Caili Guo , Chunyan Feng , Osvaldo Simeone

Despite significant advancements, large language models (LLMs) still struggle with providing accurate answers when lacking domain-specific or up-to-date knowledge. Retrieval-Augmented Generation (RAG) addresses this limitation by…

Cryptography and Security · Computer Science 2025-04-01 Yuefeng Peng , Junda Wang , Hong Yu , Amir Houmansadr

Gradient optimization-based adversarial attack methods automate the learning of adversarial triggers to generate jailbreak prompts or leak system prompts. In this work, we take a closer look at the optimization objective of adversarial…

Machine Learning · Computer Science 2025-11-21 Zhe Wang , Yanjun Qi

We present an experimental recipe for studying the relationship between training data and language model (LM) behavior. We outline steps for intervening on data batches -- i.e., ``rewriting history'' -- and then retraining model checkpoints…

Computation and Language · Computer Science 2026-05-20 Rahul Nadkarni , Yanai Elazar , Hila Gonen , Noah A. Smith

Membership inference attacks (MIAs) are widely used to empirically assess privacy risks in machine learning models, both providing model-level vulnerability metrics and identifying the most vulnerable training samples. State-of-the-art…

Machine Learning · Computer Science 2025-06-13 Joseph Pollock , Igor Shilov , Euodia Dodd , Yves-Alexandre de Montjoye

Vision-Language Models (VLMs), built on pre-trained vision encoders and large language models (LLMs), have shown exceptional multi-modal understanding and dialog capabilities, positioning them as catalysts for the next technological…

Cryptography and Security · Computer Science 2025-02-10 Yuke Hu , Zheng Li , Zhihao Liu , Yang Zhang , Zhan Qin , Kui Ren , Chun Chen

In automatic speech recognition (ASR) rescoring, the hypothesis with the fewest errors should be selected from the n-best list using a language model (LM). However, LMs are usually trained to maximize the likelihood of correct word…

Computation and Language · Computer Science 2021-10-06 Hayato Futami , Hirofumi Inaguma , Masato Mimura , Shinsuke Sakai , Tatsuya Kawahara

As agentic AI becomes more widespread, agents with distinct and possibly conflicting goals will interact in complex ways. These multi-agent interactions pose a fundamental challenge, particularly in social dilemmas, where agents' individual…

Machine Learning · Computer Science 2025-12-02 Dereck Piche , Mohammed Muqeeth , Milad Aghajohari , Juan Duque , Michael Noukhovitch , Aaron Courville

Function call capabilities have become crucial for Large Language Models (LLMs), enabling them to interact more effectively with external tools and APIs. Existing methods for improving the function call capabilities of LLMs rely on data…

Artificial Intelligence · Computer Science 2026-01-28 Weiran Guo , Bing Bo , Shaoxiang Wu , Jingsheng Yang

Membership inference attacks (MIA) aim to infer whether a particular data point is part of the training dataset of a model. In this paper, we propose a new task in the context of LLM privacy: entity-level discovery of membership risk…

Machine Learning · Computer Science 2025-11-04 Ali Satvaty , Suzan Verberne , Fatih Turkmen

Image AutoRegressive generation has emerged as a new powerful paradigm with image autoregressive models (IARs) matching state-of-the-art diffusion models (DMs) in image quality (FID: 1.48 vs. 1.58) while allowing for a higher generation…

Computer Vision and Pattern Recognition · Computer Science 2026-04-10 Antoni Kowalczuk , Jan Dubiński , Franziska Boenisch , Adam Dziedzic

The training data in large language models is key to their success, but it also presents privacy and security risks, as it may contain sensitive information. Detecting pre-training data is crucial for mitigating these concerns. Existing…

Computation and Language · Computer Science 2025-01-16 Cheng Wang , Yiwei Wang , Bryan Hooi , Yujun Cai , Nanyun Peng , Kai-Wei Chang

This report summarizes all the MIA experiments (Membership Inference Attacks) of the Embedding Attack Project, including threat models, experimental setup, experimental results, findings and discussion. Current results cover the evaluation…

Machine Learning · Computer Science 2024-01-26 Jiameng Pu , Zafar Takhirov

Model-based reinforcement learning (MBRL) allows solving complex tasks in a sample-efficient manner. However, no information is reused between the tasks. In this work, we propose a meta-learned addressing model called RAMa that provides…

Machine Learning · Computer Science 2021-10-27 Artem Zholus , Aleksandr I. Panov

Data selection for finetuning Large Language Models (LLMs) can be framed as a budget-constrained optimization problem: maximizing a model's downstream performance under a strict training data budget. Solving this problem is generally…

Machine Learning · Computer Science 2025-10-01 Animesh Jha , Harshit Gupta , Ananjan Nandi