Related papers: Deployment-Relevant Alignment Cannot Be Inferred f…

The growing awareness of safety concerns in large language models (LLMs) has sparked considerable interest in the evaluation of safety. This study investigates an under-explored issue about the evaluation of LLMs, namely the substantial…

Large Language Models (LLMs) have propelled groundbreaking advancements across several domains and are commonly used for text generation applications. However, the computational demands of these complex models pose significant challenges,…

Large language models~(LLMs) have greatly advanced the frontiers of artificial intelligence, attaining remarkable improvement in model capacity. To assess the model performance, a typical approach is to construct evaluation benchmarks for…

Large language models (LLMs) are increasingly deployed across high-impact domains, from clinical decision support and legal analysis to hiring and education, making fairness and bias evaluation before deployment critical. However, existing…

Alignment faking (AF) refers to a model strategically complying with a training objective to avoid behavioural modification while preserving its deployment preferences. Understanding when and why AF arises matters as models grow better at…

Large Language Models are increasingly deployed as educational tools, yet existing benchmarks focus on narrow skills and lack grounding in learning sciences. We introduce OpenLearnLM Benchmark, a theory-grounded framework evaluating LLMs…

Despite the remarkable advances of Large Language Models (LLMs) across diverse cognitive tasks, the rapid enhancement of these capabilities also introduces emergent deceptive behaviors that may induce severe risks in high-stakes…

Recent studies on the safety alignment of large language models (LLMs) have revealed that existing approaches often operate superficially, leaving models vulnerable to various adversarial attacks. Despite their significance, these studies…

Current benchmarks are inadequate for evaluating progress in reinforcement learning (RL) for large language models (LLMs).Despite recent benchmark gains reported for RL, we find that training on these benchmarks' training sets achieves…

As LLM-based systems increasingly operate as agents embedded within human social and technical systems, alignment can no longer be treated as a property of an isolated model, but must be understood in relation to the environments in which…

Agent systems often decompose a task across multiple roles, but these roles are typically specified by prompts rather than enforced by access controls. Without enforcement, a team pass rate can mask whether agents actually coordinated or…

Programming is a fundamentally interactive process, yet coding assistants are often evaluated using static benchmarks that fail to measure how well models collaborate with users. We introduce an interactive evaluation pipeline to examine…

Alignment faking is a form of strategic deception in AI in which models selectively comply with training objectives when they infer that they are in training, while preserving different behavior outside training. The phenomenon was first…

Processes are a crucial artefact in organizations, since they coordinate the execution of activities so that products and services are provided. The use of models to analyse the underlying processes is a well-known practice. However, due to…

Public agencies are beginning to consider large language models (LLMs) as decision-support tools for grant evaluation. This creates a practical governance problem: the model and scoring rubric should not be exposed in a way that allows…

Large language models (LLMs) are becoming increasingly capable at small parameter scales. At the same time, conventional cloud-centric deployment introduces challenges around data privacy, latency, and cost that are acute in operational…

Language models can distinguish between testing and deployment phases -- a capability known as evaluation awareness. This has significant safety and policy implications, potentially undermining the reliability of evaluations that are…

Large language model (LLM) agents are increasingly expected to operate in enterprise environments, where work is distributed across specialized roles, permission-controlled systems, and cross-departmental procedures. However, existing…

Overconfidence is a common issue for deep neural networks, limiting their deployment in real-world applications. To better estimate confidence, existing methods mostly focus on fully-supervised scenarios and rely on training labels. In this…

Language models (LMs) are increasingly used as simulacra for people, yet their ability to match the distribution of views of a specific demographic group and be \textit{distributionally aligned} remains uncertain. This notion of…