相关论文: Beyond Static Benchmarks: Synthesizing Harmful Con…

Considerable research efforts have been devoted to ensuring that large language models (LLMs) align with human values and generate safe text. However, an excessive focus on sensitivity to certain topics can compromise the model's robustness…

The scarcity of high-quality annotated medical data, particularly in mental health, poses a significant bottleneck for training robust machine learning models. Privacy regulations restrict data sharing, making synthetic data generation a…

Evaluating aligned large language models' (LLMs) ability to recognize and reject unsafe user requests is crucial for safe, policy-compliant deployments. Existing evaluation efforts, however, face three limitations that we address with…

Multimodal Large Language Models (MLLMs) are showing strong safety concerns (e.g., generating harmful outputs for users), which motivates the development of safety evaluation benchmarks. However, we observe that existing safety benchmarks…

Large Language Models (LLMs), despite extensive pretraining on broad internet corpora, often struggle to adapt effectively to specialized domains. There is growing interest in fine-tuning these models for such domains; however, progress is…

Large language models (LLMs) have shown great potential as general-purpose AI assistants in various domains. To meet the requirements of different applications, LLMs are often customized by further fine-tuning. However, the powerful…

Large Language Models (LLMs) have shown promising performance in time series modeling tasks, but do they truly understand time series data? While multiple benchmarks have been proposed to answer this fundamental question, most are manually…

Large language models (LLMs) with extended context windows have made significant strides yet remain a challenge due to the scarcity of long documents. Existing methods tend to synthesize long-context data but lack a clear mechanism to…

Large Language Models (LLMs) are increasingly vulnerable to a sophisticated form of adversarial prompting known as camouflaged jailbreaking. This method embeds malicious intent within seemingly benign language to evade existing safety…

With the rise of Large Language Models (LLMs) and their ubiquitous deployment in diverse domains, measuring language model behavior on realistic data is imperative. For example, a company deploying a client-facing chatbot must ensure that…

Language models trained on large-scale unfiltered datasets curated from the open web acquire systemic biases, prejudices, and harmful views from their training data. We present a methodology for programmatically identifying and removing…

Evaluating the performance of Large Language Models (LLMs) is a critical yet challenging task, particularly when aiming to avoid subjective assessments. This paper proposes a framework for leveraging subjective metrics derived from the…

Simulating human profiles by instilling personas into large language models (LLMs) is rapidly transforming research in agentic behavioral simulation, LLM personalization, and human-AI alignment. However, most existing synthetic personas…

Large language models (LLMs) are equipped with safety mechanisms to detect and block harmful queries, yet current alignment approaches primarily focus on overtly dangerous content and overlook more subtle threats. However, users can often…

Large language model (LLM)-based agents are increasingly used to solve complex tasks involving tool use, such as web browsing, code execution, and data analysis. However, current evaluation benchmarks do not adequately assess their ability…

Data filtering strategies are a crucial component to develop safe Large Language Models (LLM), since they support the removal of harmful contents from pretraining datasets. There is a lack of research on the actual impact of these…

Millions of individuals' well-being are challenged by the harms of substance use. Harm reduction as a public health strategy is designed to improve their health outcomes and reduce safety risks. Some large language models (LLMs) have…

The rapid advancement of multimodal large language models (MLLMs) has significantly enhanced performance across benchmarks. However, data contamination-unintentional memorization of benchmark data during model training-poses critical…

Longitudinal health agents must reason across multi-source trajectories that combine continuous device streams, sparse clinical exams, and episodic life events - yet evaluating them is hard: real-world data cannot be released at scale, and…

Evaluating AI systems that interact with humans requires understanding their behavior across diverse user populations, but collecting representative human data is often expensive or infeasible, particularly for novel technologies or…