相关论文: SAGE-RT: Synthetic Alignment data Generation for S…

Red teaming assesses how large language models (LLMs) can produce content that violates norms, policies, and rules set during their safety training. However, most existing automated methods in the literature are not representative of the…

Training models on synthetic data has emerged as an increasingly important strategy for improving the performance of generative AI. This approach is particularly helpful for large multimodal models (LMMs) due to the relative scarcity of…

Agentic LLM systems equipped with persistent memory, RAG pipelines, and external tool connectors face a class of attacks - Logic-layer Prompt Control Injection (LPCI) - for which no automated red-teaming instrument existed. We present LAAF…

Triage is a critically important decision-making process in mass casualty incidents (MCIs) to maximize victim survival rates. While the role of AI in such situations is gaining attention for making optimal decisions within limited resources…

Large Language Models (LLMs) are widely used for automated code generation. Their reliance on infrequently updated pretraining data leaves them unaware of newly discovered vulnerabilities and evolving security standards, making them prone…

Despite notable advancements in Retrieval-Augmented Generation (RAG) systems that expand large language model (LLM) capabilities through external retrieval, these systems often struggle to meet the complex and diverse needs of real-world…

The emergence of large language models (LLMs), such as Generative Pre-trained Transformer 4 (GPT-4) used by ChatGPT, has profoundly impacted the academic and broader community. While these models offer numerous advantages in terms of…

Retrieval-Augmented Generation (RAG) is a powerful approach that enables large language models (LLMs) to incorporate external knowledge. However, evaluating the effectiveness of RAG systems in specialized scenarios remains challenging due…

Large language model (LLM) driven synthetic data generation has emerged as a powerful method for improving model reasoning capabilities. However, most methods either distill large state-of-the-art models into small students or use natural…

While Retrieval-Augmented Generation (RAG) is increasingly adopted to ground Large Language Models (LLMs) in software artifacts, the optimal configuration of its components remains an open question for software engineering (SE) tasks. The…

The rapid integration of Multimodal Large Language Models (MLLMs) into critical applications is increasingly hindered by persistent safety vulnerabilities. However, existing red-teaming benchmarks are often fragmented, limited to…

We introduce a lightweight yet highly effective safety guardrail framework for language models, demonstrating that small-scale language models can achieve, and even surpass, the performance of larger counterparts in content moderation…

While modern Requirements Engineering (RE) heavily relies on natural language processing and Machine Learning (ML) techniques, their effectiveness is limited by the scarcity of high-quality datasets. This paper introduces Synthline, a…

Electromyography (EMG)-based gesture recognition has emerged as a promising approach for human-computer interaction. However, its performance is often limited by the scarcity of labeled EMG data, significant cross-user variability, and poor…

Reasoning models have demonstrated remarkable capabilities in complex reasoning tasks. However, ensuring their safety against adversarial jailbreak prompts remains a critical challenge. Due to the covert and deceptive nature of such…

Stereotactic radiosurgery (SRS) demands precise dose shaping around critical structures, yet black-box AI systems have limited clinical adoption due to opacity concerns. We tested whether chain-of-thought reasoning improves agentic planning…

Data scarcity remains a significant challenge in the field of emotion recognition using physiological signals, as acquiring comprehensive and diverse datasets is often prevented by privacy concerns and logistical constraints. This…

As large language models (LLMs) are applied to more use cases, creating high quality, task-specific datasets for fine-tuning becomes a bottleneck for model improvement. Using high quality human data has been the most common approach to…

Large language models (LLMs) have made significant advancements across various tasks, but their safety alignment remain a major concern. Exploring jailbreak prompts can expose LLMs' vulnerabilities and guide efforts to secure them. Existing…

Recent advancements in generative AI facilitate large-scale synthetic data generation for model evaluation. However, without targeted approaches, these datasets often lack the sociotechnical nuance required for sensitive domains. We…