相关论文: Below-Chance Blindness: Prompted Underperformance …

Large language models (LLMs) have shown remarkable adaptability to diverse tasks, by leveraging context prompts containing instructions, or minimal input-output examples. However, recent work revealed they also exhibit label bias -- an…

Prior behavioural work suggests that some LLMs alter choices when options are framed as causing pain or pleasure, and that such deviations can scale with stated intensity. To bridge behavioural evidence (what the model does) with…

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…

Precise estimation of downstream performance in large language models (LLMs) prior to training is essential for guiding their development process. Scaling laws analysis utilizes the statistics of a series of significantly smaller sampling…

Current literature suggests that alignment faking (deceptive alignment) is an emergent property of large language models. We present the first empirical evidence that a small instruction-tuned model, specifically LLaMA 3 8B, can exhibit…

Recent advancements in artificial intelligence have led to the creation of highly capable large language models (LLMs) that can perform tasks in a human-like manner. However, LLMs exhibit only infant-level cognitive abilities in certain…

The paradigm of scaling Large Language Models (LLMs) in both parameter size and test time has pushed the boundaries of AI capabilities, but at the cost of making the traditional generative evaluation paradigm prohibitively expensive,…

Large language models demonstrate strong performance on mathematical reasoning benchmarks, yet remain surprisingly fragile to meaning-preserving surface perturbations. We systematically evaluate three open-weight LLMs, Mistral-7B,…

Safety risks of AI models have been widely studied at deployment time, such as jailbreak attacks that elicit harmful outputs. In contrast, safety risks emerging during training remain largely unexplored. Beyond explicit reward hacking that…

Background Large language models (LLMs) are increasingly deployed in medical consultations, yet their safety under realistic user pressures remains understudied. Prior assessments focused on neutral conditions, overlooking vulnerabilities…

Large reasoning models (LRMs) with multi-step reasoning capabilities have shown remarkable problem-solving abilities, yet they exhibit concerning safety vulnerabilities that remain poorly understood. In this work, we investigate why safety…

Recent progress in end-to-end Imitation Learning approaches has shown promising results and generalization capabilities on mobile manipulation tasks. Such models are seeing increasing deployment in real-world settings, where scaling up…

Small Language Models (SLMs) are increasingly being deployed in resource-constrained environments, yet their behavioral robustness to data contamination during instruction tuning remains poorly understood. We systematically investigate the…

LLM-as-a-Judge has become a dominant approach in automated evaluation systems, playing critical roles in model alignment, leaderboard construction, quality control, and so on. However, the scalability and trustworthiness of this approach…

Large Language Model (LLM) safety guardrail models have emerged as a primary defense mechanism against harmful content generation, yet their robustness against sophisticated adversarial attacks remains poorly characterized. This study…

Large language models (LLMs) frequently refuse to respond to pseudo-malicious instructions: semantically harmless input queries triggering unnecessary LLM refusals due to conservative safety alignment, significantly impairing user…

Large Language Models (LLMs) exhibit position bias systematically underweighting information based on its location in the context but how this bias varies across languages and models remains unclear. We conduct a multilingual study across…

Interpretability and explainability of AI are becoming increasingly important in light of the rapid development of large language models (LLMs). This paper investigates the interpretation of LLMs in the context of the knowledge-based…

The emergence of Small Language Models (SLMs) as privacy-preserving alternatives for sensitive applications raises a fundamental question about their inherent understanding capabilities compared to Large Language Models (LLMs). This paper…

While prior work has focused on projecting adversarial examples back onto the manifold of natural data to restore safety, we argue that a comprehensive understanding of AI safety requires characterizing the unsafe regions themselves. This…