相关论文: STaR: Sensitive Trajectory Regulation for Unlearni…

Traditional language model-based theorem proving assumes that by training on a sufficient amount of formal proof data, a model will learn to prove theorems. Our key observation is that a wealth of informal information that is not present in…

Large language model (LLM) unlearning has become a critical topic in machine learning, aiming to eliminate the influence of specific training data or knowledge without retraining the model from scratch. A variety of techniques have been…

Large language models can exhibit emergent reasoning behaviors, often manifested as recurring lexical patterns (e.g., "wait," indicating verification). However, complex reasoning trajectories remain sparse in unconstrained sampling, and…

The widespread popularity of Large Language Models (LLMs), partly due to their unique ability to perform in-context learning, has also brought to light the importance of ethical and safety considerations when deploying these pre-trained…

Steering vectors offer a training-free mechanism for controlling reasoning behaviors in large language models, but constructing effective vectors requires identifying genuine behavioral signals in the model's hidden states. For behaviors…

The rapid development of Multimodal Large Reasoning Models (MLRMs) has demonstrated broad application potential, yet their safety and reliability remain critical concerns that require systematic exploration. To address this gap, we conduct…

Large Reasoning Models (LRMs) demonstrate exceptional capability in tackling complex mathematical, logical, and coding tasks by leveraging extended Chain-of-Thought (CoT) reasoning. Test-time scaling methods, such as prolonging CoT with…

As large reasoning models (LRMs) grow more capable, chain-of-thought (CoT) reasoning introduces new safety challenges. Existing SFT-based safety alignment studies dominantly focused on filtering prompts with safe, high-quality responses,…

Large Language Models (LLMs) have achieved strong performance across a wide range of natural language processing tasks in recent years, including machine translation, text generation, and question answering. As their applications extend to…

Over the last year, significant advancements have been made in the realms of large language models (LLMs) and multi-modal large language models (MLLMs), particularly in their application to autonomous driving. These models have showcased…

Large language models (LLMs) have demonstrated remarkable capabilities in complex reasoning tasks. However, they remain highly susceptible to jailbreak attacks that undermine their safety alignment. Existing defense mechanisms typically…

Large Reasoning Models (LRMs) have emerged as a powerful advancement in multi-step reasoning tasks, offering enhanced transparency and logical consistency through explicit chains of thought (CoT). However, these models introduce novel…

Although language models (LMs) demonstrate exceptional capabilities on various tasks, they are potentially vulnerable to extraction attacks, which represent a significant privacy risk. To mitigate the privacy concerns of LMs, machine…

Chain-of-Thought (CoT) prompting enables complex reasoning in large language models (LLMs), including applications in information retrieval (IR). However, it often leads to overthinking, where models produce excessively long and…

This paper introduces STAR-1, a high-quality, just-1k-scale safety dataset specifically designed for large reasoning models (LRMs) like DeepSeek-R1. Built on three core principles -- diversity, deliberative reasoning, and rigorous filtering…

The rise of reinforcement learning (RL) in critical real-world applications demands a fundamental rethinking of privacy in AI systems. Traditional privacy frameworks, designed to protect isolated data points, fall short for sequential…

Large language models (LLMs) exhibit remarkable generative capabilities but raise ethical and security concerns by memorizing sensitive data, reinforcing biases, and producing harmful content. These risks have spurred interest in LLM…

Large Language Models (LLMs) are increasingly deployed in politically sensitive environments, where memorisation of personal data or confidential content raises regulatory concerns under frameworks such as the GDPR and its Right to be…

Recent LLMs increasingly integrate reasoning mechanisms like Chain-of-Thought (CoT). However, this explicit reasoning exposes a new attack surface for inference-time backdoors, which inject malicious reasoning paths without altering model…

Large Reasoning Models (LRMs) demonstrate strong performance on complex tasks but often suffer from excessive verbosity, known as "overthinking." Existing solutions via reinforcement learning (RL) typically penalize generated tokens to…