Related papers: Cultural Value Alignment Via Latent Activation Ste…

Despite significant progress in alignment, large language models (LLMs) remain vulnerable to adversarial attacks that elicit harmful behaviors. Activation steering techniques offer a promising inference-time intervention approach, but…

Large language models (LLMs) are increasingly proposed as agents in strategic decision environments, yet their behavior in structured geopolitical simulations remains under-researched. We evaluate six popular state-of-the-art LLMs alongside…

The awareness of multi-cultural human values is critical to the ability of language models (LMs) to generate safe and personalized responses. However, this awareness of LMs has been insufficiently studied, since the computer science…

The advanced reasoning capabilities of Large Reasoning Models enable them to thoroughly understand and apply safety policies through deliberate thought processes, thereby improving the models' safety. Beyond safety, these models must also…

As Vision-Language Models (VLMs) achieve widespread deployment across diverse cultural contexts, ensuring their cultural competence becomes critical for responsible AI systems. While prior work has evaluated cultural awareness in text-only…

Large Language Models (LLMs) have achieved remarkable success across diverse natural language tasks, yet the reward models employed for aligning LLMs often encounter challenges of reward hacking, where the approaches predominantly rely on…

While large language models (LLMs) excel in mathematical and code reasoning, we observe they struggle with social reasoning tasks, exhibiting cognitive confusion, logical inconsistencies, and conflation between objective world states and…

Vision-Language Models (VLMs) have demonstrated impressive capabilities across a range of tasks, yet concerns about their potential biases exist. This work investigates the extent to which prominent VLMs exhibit cultural biases by…

Large Language Models (LLMs) have shown promise in simulating human behavior, yet existing agents often exhibit behavioral rigidity, a flaw frequently masked by the self-referential bias of current "LLM-as-a-judge" evaluations. By…

Large Language Models (LLMs) are widely used by software engineers for programming tasks. However, research shows that LLMs often lack a deep understanding of program semantics. Even minor changes to syntax, such as renaming variables, can…

The widespread application of LLMs across various tasks and fields has necessitated the alignment of these models with human values and preferences. Given various approaches of human value alignment, there is an urgent need to understand…

Latent space steering methods provide a practical approach to controlling large language models by applying steering vectors to intermediate activations, guiding outputs toward desired behaviors while avoiding retraining. Despite their…

Recent progress in large language models (LLMs) has focused on producing responses that meet human expectations and align with shared values - a process coined alignment. However, aligning LLMs remains challenging due to the inherent…

While cultural alignment has increasingly become a focal point within AI research, current approaches relying predominantly on quantitative benchmarks and simplistic proxies fail to capture the deeply nuanced and context-dependent nature of…

Large Language Models (LLMs) are increasingly employed in software engineering tasks such as requirements elicitation, design, and evaluation, raising critical questions regarding their alignment with human judgments on responsible AI…

Although large language models (LLMs) are increasingly implicated in interpersonal and societal decision-making, their ability to navigate explicit conflicts between legitimately different cultural value systems remains largely unexamined.…

With the wide application of large language models (LLMs), the problems of bias and value inconsistency in sensitive domains have gradually emerged, especially in terms of race, society and politics. In this paper, we propose an adversarial…

Developing value-aligned AI agents is a complex undertaking and an ongoing challenge in the field of AI. Specifically within the domain of Large Language Models (LLMs), the capability to consolidate multiple independently trained dialogue…

Despite recent advancements in Multi-modal Large Language Models (MLLMs) on diverse understanding tasks, these models struggle to solve problems which require extensive multi-step reasoning. This is primarily due to the progressive dilution…

Predicting human behavior in shared environments is crucial for safe and efficient human-robot interaction. Traditional data-driven methods to that end are pre-trained on domain-specific datasets, activity types, and prediction horizons. In…