Related papers: Domain Private Transformers for Multi-Domain Dialo…
Human conversation is inherently complex, often spanning many different topics/domains. This makes policy learning for dialogue systems very challenging. Standard flat reinforcement learning methods do not provide an efficient framework for…
Parameter-transfer is a well-known and versatile approach for meta-learning, with applications including few-shot learning, federated learning, and reinforcement learning. However, parameter-transfer algorithms often require sharing models…
This paper presents a hierarchical multi-agent LLM architecture to bridge communication gaps between non-technical end users and telecommunications domain experts in private network environments. We propose a cross-domain query translation…
Fine-tuning large language models (LLMs) for specific tasks introduces privacy risks, as models may inadvertently memorise and leak sensitive training data. While Differential Privacy (DP) offers a solution to mitigate these risks, it…
Model adaptation is crucial to handle the discrepancy between proxy training data and actual users data received. To effectively perform adaptation, textual data of users is typically stored on servers or their local devices, where…
A common way to use large pre-trained language models for downstream tasks is to fine tune them using additional layers. This may not work well if downstream domain is a specialized domain whereas the large language model has been…
Leakage of data from publicly available Machine Learning (ML) models is an area of growing significance as commercial and government applications of ML can draw on multiple sources of data, potentially including users' and clients'…
Sequential multi-agent large language model (LLM) systems are increasingly deployed in sensitive domains such as healthcare, finance, and enterprise decision-making, where multiple specialized agents collaboratively process a single user…
We study knowledge-grounded dialogue generation with pre-trained language models. Instead of pursuing new state-of-the-art on benchmarks, we try to understand if the knowledge stored in parameters of the pre-trained models is already enough…
In-context learning (ICL) in Large Language Models (LLMs) has shown remarkable performance across various tasks without requiring fine-tuning. However, recent studies have highlighted the risk of private data leakage through the prompt in…
Models trained on large unlabeled corpora of human interactions will learn patterns and mimic behaviors therein, which include offensive or otherwise toxic behavior and unwanted biases. We investigate a variety of methods to mitigate these…
In this work, we propose information laundering, a novel framework for enhancing model privacy. Unlike data privacy that concerns the protection of raw data information, model privacy aims to protect an already-learned model that is to be…
Client-side privacy rewriting is crucial for deploying LLMs in privacy-sensitive domains. However, existing approaches struggle to balance privacy and utility. Full-text methods often distort context, while span-level approaches rely on…
We study (differentially) private federated learning (FL) of language models. The language models in cross-device FL are relatively small, which can be trained with meaningful formal user-level differential privacy (DP) guarantees when…
We identify a novel phenomenon in language models: benign fine-tuning of frontier models can lead to privacy collapse. We find that diverse, subtle patterns in training data can degrade contextual privacy, including optimisation for…
Large Language Models (LLMs) trained on massive data capture rich information embedded in the training data. However, this also introduces the risk of privacy leakage, particularly involving personally identifiable information (PII).…
The leakage of data might have been an extreme effect on the personal level if it contains sensitive information. Common prevention methods like encryption-decryption, endpoint protection, intrusion detection system are prone to leakage.…
Transfer learning methods, and in particular domain adaptation, help exploit labeled data in one domain to improve the performance of a certain task in another domain. However, it is still not clear what factors affect the success of domain…
Large Language Models (LLMs) are increasingly deployed in sensitive domains including healthcare, legal services, and confidential communications, where privacy is paramount. This paper introduces Whisper Leak, a side-channel attack that…
Existing dialog systems are all monolingual, where features shared among different languages are rarely explored. In this paper, we introduce a novel multilingual dialogue system. Specifically, we augment the sequence to sequence framework…