Related papers: Consistent but Dangerous: Per-Sample Safety Classi…

Large language models deployed as agents increasingly interact with external systems through tool calls--actions with real-world consequences that text outputs alone do not carry. Safety evaluations, however, overwhelmingly measure…

As large language models (LLMs) become ubiquitous in our daily tasks and digital interactions, associated privacy risks are increasingly in focus. While LLM privacy research has primarily focused on the leakage of model training data, it…

Achieving both high safety and high usefulness simultaneously in large language models has become a critical challenge in recent years.Models often exhibit unsafe behavior or adopt an overly cautious approach leading to frequent overrefusal…

Large language models (LLMs) are now largely involved in software development workflows, and the code they generate routinely includes third-party library (TPL) imports annotated with specific version identifiers. These version choices can…

Vision-language models (VLMs) show promise in drafting radiology reports, yet they frequently suffer from logical inconsistencies, generating diagnostic impressions unsupported by their own perceptual findings or missing logically entailed…

Large language models (LLMs) are increasingly deployed in domains where errors carry high social, scientific, or safety costs. Yet standard confidence estimators, such as token likelihood, semantic similarity and multi-sample consistency,…

Modern generative and vision-language models (VLMs) are increasingly used in scientific and medical decision support, where predicted probabilities must be both accurate and well calibrated. Despite strong empirical results with moderate…

Lifelong multimodal agents must continuously adapt to new tasks through post-training, but this creates a fundamental tension between acquiring capabilities and preserving safety alignment. We demonstrate that fine-tuning aligned…

Large Language Models (LLMs) are increasingly adopted in high-stakes scenarios, yet their safety mechanisms often remain fragile. Simple jailbreak prompts or even benign fine-tuning can bypass these protocols, underscoring the need to…

Large language models (LLMs) have been used in many application domains, including cyber security. The application of LLMs in the cyber security domain presents significant opportunities, such as for enhancing threat analysis and malware…

Large Language Models (LLMs) have achieved tremendous success in various tasks, yet concerns about their safety and security have emerged. In particular, they pose risks of generating harmful content and are vulnerable to jailbreaking…

Despite their impressive performance, large language models (LLMs) such as ChatGPT are known to pose important risks. One such set of risks arises from misplaced confidence, whether over-confidence or under-confidence, that the models have…

Benchmark scores for Large Language Models (LLMs) can be inflated by memorization of test items or near duplicates. We present a simple, protocol that probes generalization by re-evaluating models on paraphrased versions of benchmark…

Vision-Language Models (VLMs) often produce self-reflective statements like "let me check the figure again" during reasoning. Do such statements trigger genuine visual re-examination, or are they merely learned textual patterns? We…

Multimodal Large Language Models (MLLMs) have tremendous potential to improve the accuracy, availability, and cost-effectiveness of healthcare by providing automated solutions or serving as aids to medical professionals. Despite promising…

As the performance of large language models (LLMs) continues to advance, their adoption in the medical domain is increasing. However, most existing risk evaluations largely focused on general safety benchmarks. In the medical applications,…

Vision-language models (VLMs) have made significant progress in recent visual-question-answering (VQA) benchmarks that evaluate complex visio-linguistic reasoning. However, are these models truly effective? In this work, we show that VLMs…

Large Language Models (LLMs) rely on safety alignment to produce socially acceptable responses. However, this behavior is known to be brittle: further fine-tuning, even on benign or lightly contaminated data, can degrade safety and…

Large language models are increasingly being used in patient-facing medical question answering, where hallucinated outputs can vary widely in potential harm. However, existing hallucination standards and evaluation metrics focus primarily…

The increasing deployment of Large Vision-Language Models (LVLMs) raises safety concerns under potential malicious inputs. However, existing multimodal safety evaluations primarily focus on model vulnerabilities exposed by static image…