Related papers: Auditing Data Provenance in Text-Generation Models

The use of machine learning (ML) models to assess and score textual data has become increasingly pervasive in an array of contexts including natural language processing, information retrieval, search and recommendation, and credibility…

It is perhaps no longer surprising that machine learning models, especially deep neural networks, are particularly vulnerable to attacks. One such vulnerability that has been well studied is model extraction: a phenomenon in which the…

Existing methods for the zero-shot detection of machine-generated text are dominated by three statistical quantities: log-likelihood, log-rank, and entropy. As language models mimic the distribution of human text ever closer, this will…

The introduction of audio latent diffusion models possessing the ability to generate realistic sound clips on demand from a text description has the potential to revolutionize how we work with audio. In this work, we make an initial attempt…

Automatic question generation is an important technique that can improve the training of question answering, help chatbots to start or continue a conversation with humans, and provide assessment materials for educational purposes. Existing…

Security verification of communication protocols in industrial and safety-critical systems is challenging because implementations are often proprietary, accessible only as black boxes, and too complex for manual modeling. As a result,…

Recent advancements in Generative AI and Large Language Models (LLMs) have enabled the creation of highly realistic synthetic content, raising concerns about the potential for malicious use, such as misinformation and manipulation.…

Unlearning algorithms aim to remove deleted data's influence from trained models at a cost lower than full retraining. However, prior guarantees of unlearning in literature are flawed and don't protect the privacy of deleted records. We…

Machine Learning and data mining techniques (i.e. supervised and unsupervised techniques) are used across domains to detect user safety violations. Examples include classifiers used to detect whether an email is spam or a web-page is…

Large language models (LLMs) possess strong semantic understanding, driving significant progress in data mining applications. This is further enhanced by large reasoning models (LRMs), which provide explicit multi-step reasoning traces. On…

Synthetic data generation is widely known to boost the accuracy of neural grammatical error correction (GEC) systems, but existing methods often lack diversity or are too simplistic to generate the broad range of grammatical errors made by…

Our research focuses on the crucial challenge of discerning text produced by Large Language Models (LLMs) from human-generated text, which holds significance for various applications. With ongoing discussions about attaining a model with…

Language generation models' democratization benefits many domains, from answering health-related questions to enhancing education by providing AI-driven tutoring services. However, language generation models' democratization also makes it…

Computational modeling plays an essential role in the study of language emergence. It aims to simulate the conditions and learning processes that could trigger the emergence of a structured language within a simulated controlled…

Components of machine learning systems are not (yet) perceived as security hotspots. Secure coding practices, such as ensuring that no execution paths depend on confidential inputs, have not yet been adopted by ML developers. We initiate…

In this paper, we investigate data augmentation for text generation, which we call GenAug. Text generation and language modeling are important tasks within natural language processing, and are especially challenging for low-data regimes. We…

Large Language Models (LLMs) are used for many tasks, including those related to coding. An important aspect of being able to utilize LLMs is the ability to assess their fitness for specific usages. The common practice is to evaluate LLMs…

Recent advancements in natural language generation has raised serious concerns. High-performance language models are widely used for language generation tasks because they are able to produce fluent and meaningful sentences. These models…

Educators have started to turn to Generative AI (GenAI) to help create new course content, but little is known about how they should do so. In this project, we investigated the first steps for optimizing content creation for advanced math.…

Textual backdoor attacks pose a practical threat to existing systems, as they can compromise the model by inserting imperceptible triggers into inputs and manipulating labels in the training dataset. With cutting-edge generative models such…