相关论文: Controllable Reasoning Models Are Private Thinkers

Chain of Thought (CoT) prompting can encourage language models to engage in multi-step logical reasoning. The quality of the provided demonstrations significantly influences the success of downstream inference tasks. Current unsupervised…

Reinforcement-learned reasoning has powered recent AI leaps on verifiable tasks, including mathematics, code, and structure prediction. The harder bottleneck is evaluative judgment in low-verifiability domains, where no oracle anchors…

We introduce a new class of attacks on machine learning models. We show that an adversary who can poison a training dataset can cause models trained on this dataset to leak significant private details of training points belonging to other…

Large Language Models (LLMs) represent a significant advancement in artificial intelligence, finding applications across various domains. However, their reliance on massive internet-sourced datasets for training brings notable privacy…

E-learning platforms that personalise content selection with AI are often criticised for lacking transparency and controllability. Researchers have therefore proposed solutions such as open learner models and letting learners select from…

Recent advances in AI reasoning models provide unprecedented transparency into their decision-making processes, transforming them from traditional black-box systems into models that articulate step-by-step chains of thought rather than…

Personalization is a critical task in modern intelligent systems, with applications spanning diverse domains, including interactions with large language models (LLMs). Recent advances in reasoning capabilities have significantly enhanced…

Large language models increasingly rely on long chains of thought to improve accuracy, yet such gains come with substantial inference-time costs. We revisit token-efficient post-training and argue that existing sequence-level reward-shaping…

Existing large language models (LLMs) face challenges of following complex instructions, especially when multiple constraints are present and organized in paralleling, chaining, and branching structures. One intuitive solution, namely…

Large reasoning models with reasoning capabilities achieve state-of-the-art performance on complex tasks, but their robustness under multi-turn adversarial pressure remains underexplored. We evaluate nine frontier reasoning models under…

A hallmark property of explainable AI models is the ability to teach other agents, communicating knowledge of how to perform a task. While Large Language Models perform complex reasoning by generating explanations for their predictions, it…

Recent developments in language modeling have increased their use in various applications and domains. Language models, often trained on sensitive data, can memorize and disclose this information during privacy attacks, raising concerns…

The rise of connected personal devices together with privacy concerns call for machine learning algorithms capable of leveraging the data of a large number of agents to learn personalized models under strong privacy requirements. In this…

Transfer learning through the use of pre-trained models has become a growing trend for the machine learning community. Consequently, numerous pre-trained models are released online to facilitate further research. However, it raises…

Deep neural networks have become a primary tool for solving problems in many fields. They are also used for addressing information retrieval problems and show strong performance in several tasks. Training these models requires large,…

Models leak information about their training data. This enables attackers to infer sensitive information about their training sets, notably determine if a data sample was part of the model's training set. The existing works empirically show…

Large language models (LLMs) have shown impressive performance by generating reasoning paths before final answers, but learning such a reasoning path requires costly human supervision. To address this issue, recent studies have explored…

In machine learning, curation is used to select the most valuable data for improving both model accuracy and computational efficiency. Recently, curation has also been explored as a solution for private machine learning: rather than…

Reasoning in humans is prone to biases due to underlying motivations like identity protection, that undermine rational decision-making and judgment. This \textit{motivated reasoning} at a collective level can be detrimental to society when…

Predictive machine learning models are becoming increasingly deployed in high-stakes contexts involving sensitive personal data; in these contexts, there is a trade-off between model explainability and data privacy. In this work, we push…