Related papers: Anchoring Refusal Direction: Mitigating Safety Ris…

Despite the massive success of fine-tuning Pre-trained Language Models (PLMs), they remain susceptible to out-of-distribution input. Dataset cartography is a simple yet effective dual-model approach that improves the robustness of…

Instruction Fine-Tuning enhances pre-trained language models from basic next-word prediction to complex instruction-following. However, existing One-off Instruction Fine-Tuning (One-off IFT) method, applied on a diverse instruction, may not…

Safety alignment is a key requirement for building reliable Artificial General Intelligence. Despite significant advances in safety alignment, we observe that minor latent shifts can still trigger unsafe responses in aligned models. We…

Large Language Models (LLMs) are typically aligned for safety during the post-training phase; however, they may still generate inappropriate outputs that could potentially pose risks to users. This challenge underscores the need for robust…

Teaching large language models (LLMs) to reason during post-training typically relies on reinforcement learning with explicit outcome- or process-based reward functions. However, in many real-world settings, obtaining or defining such…

Recent large language models (LLMs) have increasingly adopted the Mixture-of-Experts (MoE) architecture for efficiency. MoE-based LLMs heavily depend on a superficial safety mechanism in which harmful inputs are routed safety-critical…

While modern LLMs are aligned to refuse harmful requests, it is essential to understand the underlying mechanistic basis of this refusal behavior for model safety analysis. For example, steering-based jailbreak attacks exploit this by…

Multimodal Large Language Models (MLLMs) are increasingly vulnerable to multimodal Indirect Prompt Injection (IPI) attacks, which embed malicious instructions in images, videos, or audio to hijack model behavior. Existing defenses, designed…

Despite the impressive performance of general-purpose large language models (LLMs), they often require fine-tuning or post-training to excel at specific tasks. For instance, large reasoning models (LRMs), such as the DeepSeek-R1 series,…

Instruction fine-tuning (IFT) elicits instruction following capabilities and steers the behavior of large language models (LLMs) via supervised learning. However, existing models trained on open-source IFT datasets only have the ability to…

Supervised open-loop training has been widely adopted for training traffic simulation models; however, it fails to capture the inherently dynamic, multi-agent interactions common in complex driving scenarios. We introduce RLFTSim, a…

Recent advances in Large Language Models (LLMs) have brought significant improvements to various service domains, including chatbots and medical pre-consultation applications. In the healthcare domain, the most common approach for adapting…

Fine-tuning pretrained models is a standard and effective workflow in modern machine learning. However, robust fine-tuning (RFT), which aims to simultaneously achieve adaptation to a downstream task and robustness to adversarial examples,…

Large Language Models (LLMs) are increasingly relied upon for complex workflows, yet their ability to maintain flow of instructions remains underexplored. Existing benchmarks conflate task complexity with structural ordering, making it…

Partial perception deficits can compromise autonomous vehicle safety by disrupting environmental understanding. Existing protocols typically default to entirely risk-avoidant actions such as immediate stops, which are detrimental to…

Prompting has shown impressive success in enabling large pretrained language models (LMs) to perform diverse NLP tasks, especially when only few downstream data are available. Automatically finding the optimal prompt for each task, however,…

Reinforcement Fine-Tuning (RFT) on flow-based models is crucial for preference alignment. However, they often introduce visual hallucinations like over-optimized details and semantic misalignment. This work preliminarily explores why visual…

Reinforcement Fine-Tuning (RFT) has established itself as a critical paradigm for the alignment of Multi-modal Large Language Models (MLLMs) with complex human values and domain-specific requirements. Nevertheless, current research…

As LLMs are increasingly deployed in real-world applications, ensuring their ability to refuse malicious prompts, especially jailbreak attacks, is essential for safe and reliable use. Recently, activation steering has emerged as an…

Large language models (LLMs) are vital for a wide range of applications yet remain susceptible to jailbreak threats, which could lead to the generation of inappropriate responses. Conventional defenses, such as refusal and adversarial…