Related papers: Domain Private Transformers for Multi-Domain Dialo…

Fine-tuning large language models on private data for downstream applications poses significant privacy risks in potentially exposing sensitive information. Several popular community platforms now offer convenient distribution of a large…

Dialog policy determines the next-step actions for agents and hence is central to a dialogue system. However, when migrated to novel domains with little data, a policy model can fail to adapt due to insufficient interactions with the new…

Large language models (LLMs) are increasingly applied in fields such as finance, education, and governance due to their ability to generate human-like text and adapt to specialized tasks. However, their widespread adoption raises critical…

Transformer-based pre-trained language models boost the performance of open-domain dialogue systems. Prior works leverage Transformer-based pre-trained language models to generate texts with desired attributes in two general approaches: (1)…

Continual pre-training has been urgent for adapting a pre-trained model to a multitude of domains and tasks in the fast-evolving world. In practice, a continually pre-trained model is expected to demonstrate not only greater capacity when…

The arms race between attacks and defenses for machine learning models has come to a forefront in recent years, in both the security community and the privacy community. However, one big limitation of previous research is that the security…

Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse natural language processing tasks, but their tendency to memorize training data poses significant privacy risks, particularly during fine-tuning…

The integration of Differential Privacy (DP) with diffusion models (DMs) presents a promising yet challenging frontier, particularly due to the substantial memorization capabilities of DMs that pose significant privacy risks. Differential…

We investigate how different domains are encoded in modern neural network architectures. We analyze the relationship between natural language domains, model size, and the amount of training data used. The primary analysis tool we develop is…

The interactive use of large language models (LLMs) in AI assistants (at work, home, etc.) introduces a new set of inference-time privacy risks: LLMs are fed different types of information from multiple sources in their inputs and are…

Mobile Large Language Models (LLMs) are revolutionizing diverse fields such as healthcare, finance, and education with their ability to perform advanced natural language processing tasks on-the-go. However, the deployment of these models in…

Large language models (LLMs) are demonstrably capable of cross-lingual transfer, but can produce inconsistent output when prompted with the same queries written in different languages. To understand how language models are able to…

Large language models (LLMs) offer strong capabilities but raise cost and privacy concerns, whereas small language models (SLMs) facilitate efficient and private local inference yet suffer from limited capacity. To synergize the…

Language Models (LMs) have been shown to leak information about training data through sentence-level membership inference and reconstruction attacks. Understanding the risk of LMs leaking Personally Identifiable Information (PII) has…

Recently, utilizing deep neural networks to build the opendomain dialogue models has become a hot topic. However, the responses generated by these models suffer from many problems such as responses not being contextualized and tend to…

This paper is focused on the language modelling for task-oriented domains and presents an accurate analysis of the utterances acquired by the Dialogos spoken dialogue system. Dialogos allows access to the Italian Railways timetable by using…

Large language models have shown unprecedented abilities in generating linguistically coherent and syntactically correct natural language output. However, they often return incorrect and inconsistent answers to input questions. Due to the…

Large language models (LLMs) are increasingly integrated into daily life through conversational interfaces, processing user data via natural language inputs and exhibiting advanced reasoning capabilities, which raises new concerns about…

Deep latent variable models have been shown to facilitate the response generation for open-domain dialog systems. However, these latent variables are highly randomized, leading to uncontrollable generated responses. In this paper, we…

Language models are deployed in settings that require compartmentalization: system prompts should not be disclosed, chain-of-thought reasoning is hidden from users, and sensitive data passes through shared contexts. We test whether models…