Related papers: Safety Under Scaffolding: How Evaluation Condition…

Neurodiverse learners often require reading supports, yet increasing scaffold richness can sometimes overload attention and working memory rather than improve comprehension. Grounded in the Construction-Integration model and a contingent…

Recent work has shown that a model's input word embeddings can serve as effective control variables for steering its behavior toward outputs that satisfy desired properties. However, this has only been demonstrated for pretrained…

Scaffolding Large Language Models (LLMs) into multi-agent systems often improves performance on complex tasks, but the safety impact of such scaffolds has not been thoroughly explored. We introduce AgentBreeder, a framework for…

Foundation models are routinely fine-tuned for use in particular domains, yet safety assessments are typically conducted only on base models, implicitly assuming that safety properties persist through downstream adaptation. We test this…

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…

Clinical LLMs are often scaled by increasing model size, context length, retrieval complexity, or inference-time compute, with the implicit expectation that higher accuracy implies safer behavior. This assumption is incomplete in medicine,…

The rapid development of Multimodal Large Reasoning Models (MLRMs) has demonstrated broad application potential, yet their safety and reliability remain critical concerns that require systematic exploration. To address this gap, we conduct…

Alignment evaluation in machine learning has largely become evaluation of models. Influential benchmarks score model outputs under fixed inputs, such as truthfulness, instruction following, or pairwise preference, and these scores are often…

Safety lies at the core of developing and deploying large language models (LLMs). However, previous safety benchmarks only concern the safety in one language, e.g. the majority language in the pretraining data such as English. In this work,…

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…

Safety benchmark scores provide incomplete evidence of deployment readiness: aligned language models often adhere to rigid rules even when a situational update flips which action is safe. We term this failure brittle safety. To diagnose it,…

This paper presents a systematic mapping study on the model-driven engineering of safety and security concerns in systems. Integrated modeling and development of both safety and security concerns is an emerging field of research. Our…

Evaluating alignment in language models requires testing how they behave under realistic pressure, not just what they claim they would do. While alignment failures increasingly cause real-world harm, comprehensive evaluation frameworks with…

This survey organizes the intricate literature on the design and optimization of emerging structures around post-trained LMs. We refer to this overarching structure as scaffolded LMs and focus on LMs that are integrated into multi-step…

AI coding assistants powered by large language models (LLMs) have transformed software development, significantly boosting productivity. While existing benchmarks evaluate the correctness and security of LLM-generated code, they are…

We survey the state-of-the-art on model-based formalisms for safety and security joint analysis, where safety refers to the absence of unintended failures, and security to absence of malicious attacks. We conduct a thorough literature…

Alignment tuning has enabled large language models to excel in reasoning, instruction-following, and minimizing harmful generations. However, despite their widespread deployment, these models exhibit a monolingual bias, raising concerns…

Fine-tuning safety-aligned large language models (LLMs) can substantially compromise their safety. Previous approaches require many safety samples or calibration sets, which not only incur significant computational overhead during…

Large language models (LLMs) are often assumed to contain ``safety regions'' -- parameter subsets whose modification directly influences safety behaviors. We conduct a systematic evaluation of four safety region identification methods…

Large language models are rapidly being deployed as AI tutors, yet current evaluation paradigms assess problem-solving accuracy and generic safety in isolation, failing to capture whether a model is simultaneously pedagogically effective…