Related papers: Memorization vs. Generalization: Quantifying Data …
Very large deep learning models trained using gradient descent are remarkably resistant to memorization given their huge capacity, but are at the same time capable of fitting large datasets of pure noise. Here methods are introduced by…
Although large language models (LLMs) have apparently acquired a certain level of grammatical knowledge and the ability to make generalizations, they fail to interpret negation, a crucial step in Natural Language Processing. We try to…
Large Language Models (LLMs) are trained on massive web-crawled corpora. This poses risks of leakage, including personal information, copyrighted texts, and benchmark datasets. Such leakage leads to undermining human trust in AI due to…
We show that in language learning, contrary to received wisdom, keeping exceptional training instances in memory can be beneficial for generalization accuracy. We investigate this phenomenon empirically on a selection of benchmark natural…
Large Language Models (LLMs) are prevalent in modern applications but often memorize training data, leading to privacy breaches and copyright issues. Existing research has mainly focused on posthoc analyses, such as extracting memorized…
The opacity in developing large language models (LLMs) is raising growing concerns about the potential contamination of public benchmarks in the pre-training data. Existing contamination detection methods are typically based on the text…
Natural language reflects our private lives and identities, making its privacy concerns as broad as those of real life. Language models lack the ability to understand the context and sensitivity of text, and tend to memorize phrases present…
Machine Learning (ML) models have been shown to potentially leak sensitive information, thus raising privacy concerns in ML-driven applications. This inspired recent research on removing the influence of specific data samples from a trained…
While Large Language Models (LLMs) have demonstrated exceptional multitasking abilities, fine-tuning these models on downstream, domain-specific datasets is often necessary to yield superior performance on test sets compared to their…
Neural language models are black-boxes--both linguistic patterns and factual knowledge are distributed across billions of opaque parameters. This entangled encoding makes it difficult to reliably inspect, verify, or update specific facts.…
Are Large Pre-Trained Language Models Leaking Your Personal Information? In this paper, we analyze whether Pre-Trained Language Models (PLMs) are prone to leaking personal information. Specifically, we query PLMs for email addresses with…
Language model (LM) agents that act on users' behalf for personal tasks (e.g., replying emails) can boost productivity, but are also susceptible to unintended privacy leakage risks. We present the first study on people's capacity to oversee…
Memorization, or the tendency of large language models (LLMs) to output entire sequences from their training data verbatim, is a key concern for safely deploying language models. In particular, it is vital to minimize a model's memorization…
Language models (LMs) trained on large amounts of data have shown impressive performance on many NLP tasks under the zero-shot and few-shot setup. Here we aim to better understand the extent to which such models learn commonsense knowledge…
Large language models, trained on massive corpora, are prone to verbatim memorization of training data, creating significant privacy and copyright risks. While previous works have proposed various definitions for memorization, many exhibit…
Large language models (LLMs) risk retaining unauthorized or sensitive information from their training data, which raises privacy concerns. LLM unlearning seeks to mitigate these risks by selectively removing specified data while maintaining…
State-of-the-art NLP models can adopt shallow heuristics that limit their generalization capability (McCoy et al., 2019). Such heuristics include lexical overlap with the training set in Named-Entity Recognition (Taill\'e et al., 2020) and…
Data used to train supervised machine learning models are commonly split into independent training, validation, and test sets. This paper illustrates that complex data leakage cases have occurred in the no-reference image and video quality…
State-of-the-art supervised NLP models achieve high accuracy but are also susceptible to failures on inputs from low-data regimes, such as domains that are not represented in training data. As an approximation to collecting ground-truth…
Federated learning (FL) enables collaborative training without raw data sharing, but still risks training data memorization. Existing FL memorization detection techniques focus on one sample at a time, underestimating more subtle risks of…