English
Related papers

Related papers: Detecting and Filtering Unsafe Training Data via D…

200 papers

The black-box nature of large language models (LLMs) poses challenges in interpreting results, impacting issues such as data intellectual property protection and hallucination tracing. Training data attribution (TDA) methods are considered…

Computation and Language · Computer Science 2024-11-20 Kangxi Wu , Liang Pang , Huawei Shen , Xueqi Cheng

Training data attribution (TDA) methods aim to identify which training examples influence a model's predictions on specific test data most. By quantifying these influences, TDA supports critical applications such as data debugging,…

Machine Learning · Computer Science 2025-05-30 Xingyuan Pan , Chenlu Ye , Joseph Melkonian , Jiaqi W. Ma , Tong Zhang

Training data attribution (TDA) plays a critical role in understanding the influence of individual training data points on model predictions. Gradient-based TDA methods, popularized by \textit{influence function} for their superior…

Machine Learning · Computer Science 2025-09-17 Shiyuan Zhang , Junwei Deng , Juhan Bae , Jiaqi Ma

Many training data attribution (TDA) methods aim to estimate how a model's behavior would change if one or more data points were removed from the training set. Methods based on implicit differentiation, such as influence functions, can be…

Machine Learning · Computer Science 2024-05-22 Juhan Bae , Wu Lin , Jonathan Lorraine , Roger Grosse

Training data attribution (TDA) methods aim to measure how training data impacts a model's predictions. While gradient-based attribution methods, such as influence functions, offer theoretical grounding, their computational costs make them…

Machine Learning · Computer Science 2025-11-27 Weiwei Sun , Haokun Liu , Nikhil Kandpal , Colin Raffel , Yiming Yang

We propose probe-based data attribution, a method that traces behavioral changes in post-trained language models to responsible training datapoints. By computing activation-difference vectors for both test prompts and preference pairs and…

Machine Learning · Computer Science 2026-04-28 Frank Xiao , Santiago Aranguri

Training data attribution (TDA) methods aim to attribute model outputs back to specific training examples, and the application of these methods to large language model (LLM) outputs could significantly advance model transparency and data…

Computation and Language · Computer Science 2024-12-24 Tyler A. Chang , Dheeraj Rajagopal , Tolga Bolukbasi , Lucas Dixon , Ian Tenney

While large language models (LLMs) are extensively used, there are raising concerns regarding privacy, security, and copyright due to their opaque training data, which brings the problem of detecting pre-training data on the table. Current…

Computation and Language · Computer Science 2024-08-01 Anqi Zhang , Chaofeng Wu

Large Language Models (LLMs) have demonstrated remarkable capabilities, yet their deployment is frequently undermined by undesirable behaviors such as generating harmful content, factual inaccuracies, and societal biases. Diagnosing the…

Computation and Language · Computer Science 2025-10-06 Zhe Li , Wei Zhao , Yige Li , Jun Sun

Software-Defined Networking (SDN) improves network flexibility but also increases the need for reliable and interpretable intrusion detection. Large Language Models (LLMs) have recently been explored for cybersecurity tasks due to their…

Cryptography and Security · Computer Science 2026-04-09 Umesh Biswas , Shafqat Hasan , Syed Mohammed Farhan , Nisha Pillai , Charan Gudla

This study addresses a critical gap in safety tuning practices for Large Language Models (LLMs) by identifying and tackling a refusal position bias within safety tuning data, which compromises the models' ability to appropriately refuse…

Computation and Language · Computer Science 2025-05-26 Youliang Yuan , Wenxiang Jiao , Wenxuan Wang , Jen-tse Huang , Jiahao Xu , Tian Liang , Pinjia He , Zhaopeng Tu

Reinforcement learning (RL) algorithms can be divided into two classes: model-free algorithms, which are sample-inefficient, and model-based algorithms, which suffer from model bias. Dyna-style algorithms combine these two approaches by…

Machine Learning · Computer Science 2024-10-17 Yansong Li , Zeyu Dong , Ertai Luo , Yu Wu , Shuo Wu , Shuo Han

Training data attribution (TDA) is concerned with understanding model behavior in terms of the training data. This paper draws attention to the common setting where one has access only to the final trained model, and not the training…

Machine Learning · Computer Science 2025-11-25 Dennis Wei , Inkit Padhi , Soumya Ghosh , Amit Dhurandhar , Karthikeyan Natesan Ramamurthy , Maria Chang

There is growing concern over the safety of powerful diffusion models (DMs), as they are often misused to produce inappropriate, not-safe-for-work (NSFW) content or generate copyrighted material or data of individuals who wish to be…

Artificial Intelligence · Computer Science 2026-02-24 Mingyu Kim , Dongjun Kim , Amman Yusuf , Stefano Ermon , Mijung Park

The problem of pre-training data detection for large language models (LLMs) has received growing attention due to its implications in critical issues like copyright violation and test data contamination. Despite improved performance,…

Computation and Language · Computer Science 2025-02-13 Jingyang Zhang , Jingwei Sun , Eric Yeats , Yang Ouyang , Martin Kuo , Jianyi Zhang , Hao Frank Yang , Hai Li

As large language models achieve increasingly impressive results, questions arise about whether such performance is from generalizability or mere data memorization. Thus, numerous data contamination detection methods have been proposed.…

Computation and Language · Computer Science 2024-12-10 Vinay Samuel , Yue Zhou , Henry Peng Zou

Measuring domain relevance of data and identifying or selecting well-fit domain data for machine translation (MT) is a well-studied topic, but denoising is not yet. Denoising is concerned with a different type of data quality and tries to…

Computation and Language · Computer Science 2018-09-05 Wei Wang , Taro Watanabe , Macduff Hughes , Tetsuji Nakagawa , Ciprian Chelba

Reinforcement learning (RL) post-training has shown to improve reasoning in large language models (LLMs). However, there has been little exploration on the problem of data contamination in RL post-training, potentially undermining…

Machine Learning · Computer Science 2026-05-29 Minju Gwak , Minseo Kwak , Dongseok Lee , Guijin Son , Alan Ritter , Jaehyung Kim

Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) systems are increasingly deployed in industry applications, yet their reliability remains hampered by challenges in detecting hallucinations. While supervised…

Computation and Language · Computer Science 2025-05-30 Julia Belikova , Konstantin Polev , Rauf Parchiev , Dmitry Simakov

Text-to-image diffusion models have demonstrated remarkable effectiveness in rapid and high-fidelity personalization, even when provided with only a few user images. However, the effectiveness of personalization techniques has lead to…

Computer Vision and Pattern Recognition · Computer Science 2025-10-06 Naresh Kumar Devulapally , Shruti Agarwal , Tejas Gokhale , Vishnu Suresh Lokhande
‹ Prev 1 2 3 10 Next ›