Out-of-distribution (OOD) generalisation is essential for authorship attribution (AA), especially when involving new authors, yet this aspect remains insufficiently supported by existing AA datasets. In this paper, we introduce GHOSTWRITEBENCH, a dataset for LLM AA task, designed to test generalisation across multiple OOD dimensions, including unseen domain and authors. GHOSTWRITEBENCH comprises long-form texts (50K+ words per book) generated by ten frontier LLMs. We find that existing methods degrade substantially in unseen author scenarios — dropping by as much as 70% even under high-resource settings. We propose TRACE, a novel lightweight and interpretable fingerprinting method that captures token-level transition patterns (i.e., word rank and entropy) using a lightweight language model. Experiments show robustness of TRACE in OOD settings and establish it as a strong baseline on GHOSTWRITEBENCH.

As large language models are increasingly deployed in high-stakes domains, it is essential that their outputs reflect not average human preference, but diverse perspectives. Achieving such pluralism remains challenging: existing pluralistic alignment methods rely on prompt-level interventions, represent only a limited set of values, or are compute-heavy, lacking explicit value control and representation. Furthermore, existing steering methods require manual value selection and cannot dynamically adapt to scenario-dependent value requirements, limiting their scalability and generality. To address these limitations, we introduce VISPA, a training-free pluralistic alignment framework that performs automatic, context-driven value selection and modular value-steered generation. VISPA identifies scenario-relevant values dynamically and applies activation steering to produce value-conditioned responses representing distinct perspectives. These responses enable support for three pluralistic alignment modes: Overton, Steerable, and Distributional. VISPA supports the addition of new values without finetuning and is compatible with diverse steering instantiations and steering models. Across extensive experiments spanning multiple models and evaluation settings, VISPA demonstrates strong performance across all pluralistic alignment modes in healthcare and beyond.

As large language models are increasingly deployed in sensitive domains such as healthcare, ensuring their outputs reflect the diverse values and perspectives held across populations is critical. However, existing alignment approaches, including pluralistic paradigms like Modular Pluralism, often fall short in the health domain, where personal, cultural, and situational factors shape pluralism. Motivated by the aforementioned healthcare challenges, we propose a first lightweight, generalizable, pluralistic alignment approach, ETHOSAGENTS, designed to simulate diverse perspectives and values. We empirically show that it advances the pluralistic alignment for all three modes across seven varying-sized open and closed models. Our findings reveal that health-related pluralism demands adaptable and normatively aware approaches, offering insights into how these models can better respect diversity in other high-stakes domains.

Embeddings-as-a-Service (EaaS) is a service offered by large language model (LLM) developers to supply embeddings generated by LLMs. Previous research suggests that EaaS is prone to imitation attacks—attacks that clone the underlying EaaS model by training another model on the queried embeddings. As a result, EaaS watermarks are introduced to protect the intellectual property of EaaS providers. In this paper, we first show that existing EaaS watermarks can be removed by paraphrasing when attackers clone the model. Subsequently, we propose a novel watermarking technique that involves linearly transforming the embeddings, and show that it is empirically and theoretically robust against paraphrasing.

Alignment techniques have become central to ensuring that Large Language Models (LLMs) generate outputs consistent with human values. However, existing alignment paradigms often model an averaged or monolithic preference, failing to account for the diversity of perspectives across cultures, demographics, and communities. This limitation is particularly critical in health-related scenarios, where plurality is essential due to the influence of culture, religion, personal values, and conflicting opinions. Despite progress in pluralistic alignment, no prior work has focused on health, likely due to the unavailability of publicly available datasets. To address this gap, we introduce VITAL, a new benchmark dataset comprising 13.1K value-laden situations and 5.4K multiple-choice questions focused on health, designed to assess and benchmark pluralistic alignment methodologies. Through extensive evaluation of eight LLMs of varying sizes, we demonstrate that existing pluralistic alignment techniques fall short in effectively accommodating diverse healthcare beliefs, underscoring the need for tailored AI alignment in specific domains. This work highlights the limitations of current approaches and lays the groundwork for developing health-specific alignment solutions.

Embedding as a Service (EaaS) has become a widely adopted solution, which offers feature extraction capabilities for addressing various downstream tasks in Natural Language Processing (NLP). Prior studies have shown that EaaS can be prone to model extraction attacks; nevertheless, this concern could be mitigated by adding backdoor watermarks to the text embeddings and subsequently verifying the attack models post-publication. Through the analysis of the recent watermarking strategy for EaaS, EmbMarker, we design a novel CSE (Clustering, Selection, Elimination) attack that removes the backdoor watermark while maintaining the high utility of embeddings, indicating that the previous watermarking approach can be breached. In response to this new threat, we propose a new protocol to make the removal of watermarks more challenging by incorporating multiple possible watermark directions. Our defense approach, WARDEN, notably increases the stealthiness of watermarks and has been empirically shown to be effective against CSE attack.