相关论文: Leaky Thoughts: Large Reasoning Models Are Not Pri…

Recent reasoning large language models (LLMs) have demonstrated remarkable improvements in mathematical reasoning capabilities through long Chain-of-Thought. The reasoning tokens of these models enable self-correction within reasoning…

Data science pipelines to train and evaluate models with machine learning may contain bugs just like any other code. Leakage between training and test data can lead to overestimating the model's accuracy during offline evaluations, possibly…

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).…

Large Reasoning Models like DeepSeek-R1 mark a fundamental shift in how LLMs approach complex problems. Instead of directly producing an answer for a given input, DeepSeek-R1 creates detailed multi-step reasoning chains, seemingly…

Despite their wide adoption, the biases and unintended behaviors of language models remain poorly understood. In this paper, we identify and characterize a phenomenon never discussed before, which we call semantic leakage, where models leak…

Recent advances in Chain-of-Thought (CoT) prompting have substantially improved the reasoning capabilities of large language models (LLMs), but have also introduced their computational efficiency as a new attack surface. In this paper, we…

Although Large Language Models (LLMs) have become increasingly integral to diverse applications, their capabilities raise significant privacy concerns. This survey offers a comprehensive overview of privacy risks associated with LLMs and…

Pre-trained large language models, such as GPT\nobreakdash-2 and BERT, are often fine-tuned to achieve state-of-the-art performance on a downstream task. One natural example is the ``Smart Reply'' application where a pre-trained model is…

Recent work has shown that probing model internals can reveal a wealth of information not apparent from the model generations. This poses the risk of unintentional or malicious information leakage, where model users are able to learn…

Frontier AI systems are making transformative impacts across society, but such benefits are not without costs: models trained on web-scale datasets containing personal and private data raise profound concerns about data privacy and…

LLM safety evaluations predominantly test models in isolation, yet deployed AI agents increasingly operate within persistent social environments alongside other agents. We introduce a Moltbook-style simulation platform where thousands of…

Large language models (LLMs) often produce confident yet incorrect answers, which can lead to risky failures in real-world applications. We study whether post-training can make a model's self-assessment explicit: when the model is…

A major concern of Machine Learning (ML) models is their opacity. They are deployed in an increasing number of applications where they often operate as black boxes that do not provide explanations for their predictions. Among others, the…

Recently, small models with latent recursion have obtained promising results on complex reasoning tasks. These results are typically explained by the theory that such recursion increases a networks depth, allowing it to compactly emulate…

Tool-use large language model (LLM) agents are increasingly deployed to support sensitive workflows, relying on tool calls for retrieval, external API access, and session memory management. While prior research has examined various threats,…

Addressing contextual privacy concerns remains challenging in interactive settings where large language models (LLMs) process information from multiple sources (e.g., summarizing meetings with private and public information). We introduce a…

Uncertainty quantification for LLMs is a key research direction towards addressing hallucination and other issues that limit their reliable deployment. In this work, we show that reasoning trace length is a simple and useful confidence…

With the rise of advanced reasoning capabilities, large language models (LLMs) are receiving increasing attention. However, although reasoning improves LLMs' performance on downstream tasks, it also introduces new security risks, as…

Large Language Model (LLM) agents have become increasingly prevalent across various real-world applications. They enhance decision-making by storing private user-agent interactions in the memory module for demonstrations, introducing new…

Reward hacking, where a reasoning model exploits loopholes in a reward function to achieve high rewards without solving the intended task, poses a significant threat. This behavior may be explicit, i.e. verbalized in the model's…