Related papers: When Context Flips, Safety Breaks: Diagnosing Brit…

Large language models (LLMs) are now ubiquitous in everyday tools, raising urgent safety concerns about their tendency to generate harmful content. The dominant safety approach -- reinforcement learning from human feedback (RLHF) --…

A model that avoids stereotypes in a lab benchmark may not avoid them in deployment. We show that measured bias shifts dramatically when prompts mention different places, times, or audiences -- no adversarial prompting required. We…

Given the growing influence of language model-based agents on high-stakes societal decisions, from public policy to healthcare, ensuring their beneficial impact requires understanding the far-reaching implications of their suggestions. We…

Detection of carelessness in digital learning platforms has relied on the contextual slip model, which leverages conditional probability and Bayesian Knowledge Tracing (BKT) to identify careless errors, where students make mistakes despite…

Large language models are being deployed as mental health support agents at scale, yet only 16% of LLM-based chatbot interventions have undergone rigorous clinical efficacy testing, and simulations reveal psychological deterioration in over…

Adaptive prompting mechanisms have been proposed to enhance vision-language models by dynamically tailoring prompts to inputs. However, in frozen few-shot prompt learning with CLIP-style backbones, we systematically observe that adaptive…

Retrieval-augmented LLMs are deployed for tasks where evidence quality determines action safety, yet evaluation protocols assume that single-turn robustness predicts robustness when evidence accumulates across turns. We show this assumption…

We propose a new long-context financial benchmark, FailSafeQA, designed to test the robustness and context-awareness of LLMs against six variations in human-interface interactions in LLM-based query-answer systems within finance. We…

Current Large Language Models (LLMs), even those tuned for safety and alignment, are susceptible to jailbreaking. Some have found that just further fine-tuning an aligned model with benign data (i.e., data without harmful content)…

While the task of assessing the plausibility of events such as ''news is relevant'' has been addressed by a growing body of work, less attention has been paid to capturing changes in plausibility as triggered by event modification.…

Large language models (LLMs) exhibiting test-time scaling behavior, such as extended reasoning traces and self-verification, have demonstrated remarkable performance on complex, long-term reasoning tasks. However, the robustness of these…

Current language model safety paradigms often fall short in emotionally charged or high-stakes settings, where refusal-only approaches may alienate users and naive compliance can amplify risk. We propose ProSocialAlign, a test-time,…

Long-context LLMs can infer objectives that are not stated explicitly. This capability is useful for reasoning over documents, code, retrieved evidence, and tool traces, but it also creates a safety risk: harmful intent can be distributed…

Large audio-language models (LALMs) extend text-based LLMs with auditory understanding, offering new opportunities for multimodal applications. While their perception, reasoning, and task performance have been widely studied, their safety…

A core challenge in the development of increasingly capable AI systems is to make them safe and reliable by ensuring their behaviour is consistent with human values. This challenge, known as the alignment problem, does not merely apply to…

Safety-aligned language models often refuse cybersecurity requests whose wording resembles misuse, even when the task is authorized and defensive. This makes security evaluation ambiguous: a failed answer may reflect missing capability or…

As Large Language Models (LLMs) integrate into critical global infrastructure, the assumption that safety alignment transfers zero-shot from English to other languages remains a dangerous blind spot. This study presents a systematic audit…

As Multimodal Large Language Models (MLLMs) acquire stronger reasoning capabilities to handle complex, multi-image instructions, this advancement may pose new safety risks. We study this problem by introducing MIR-SafetyBench, the first…

Frontier language models sometimes recognize that they are being evaluated and adjust their behavior, undermining validity of benchmark results. Yet the field studies it without a shared foundation, conflating properties of the evaluation…

Multimodal Large Language Models (MLLMs) are rapidly evolving, demonstrating impressive capabilities as multimodal assistants that interact with both humans and their environments. However, this increased sophistication introduces…