相关论文: When Prohibitions Become Permissions: Auditing Neg…

Machine learning models always make a prediction, even when it is likely to be inaccurate. This behavior should be avoided in many decision support applications, where mistakes can have severe consequences. Albeit already studied in 1970,…

System Instructions in Large Language Models (LLMs) are commonly used to enforce safety policies, define agent behavior, and protect sensitive operational context in agentic AI applications. These instructions may contain sensitive…

In this paper, we argue for a paradigm shift from the current model of explainable artificial intelligence (XAI), which may be counter-productive to better human decision making. In early decision support systems, we assumed that we could…

Negation is a common everyday phenomena and has been a consistent area of weakness for language models (LMs). Although the Information Retrieval (IR) community has adopted LMs as the backbone of modern IR architectures, there has been…

As large language models (LLMs) are increasingly deployed in high-stakes settings, their ability to refuse ethically sensitive prompts-such as those involving hate speech or illegal activities-has become central to content moderation and…

Large language models underestimate the impact of negations on how much they change the meaning of a sentence. Therefore, learned evaluation metrics based on these models are insensitive to negations. In this paper, we propose NegBLEURT, a…

Negation has been shown to be a major bottleneck for masked language models, such as BERT. However, whether this finding still holds for larger-sized auto-regressive language models (``LLMs'') has not been studied comprehensively. With the…

Given the impressive capabilities of recent Large Language Models (LLMs), we investigate and benchmark the most popular proprietary and different sized open source models on the task of explicit instruction following in conflicting…

AI systems are increasingly intertwined with daily life, assisting users with various tasks and guiding decision-making. This integration introduces risks of AI-driven manipulation, where such systems may exploit users' cognitive biases and…

This work introduces a novel framework for evaluating LLMs' capacity to balance instruction-following with critical reasoning when presented with multiple-choice questions containing no valid answers. Through systematic evaluation across…

We probe OpenAI's open-weights 20-billion-parameter model gpt-oss-20b to study how sociopragmatic framing, language choice, and instruction hierarchy affect refusal behavior. Across 80 seeded iterations per scenario, we test several harm…

Artificial Intelligence (AI) is becoming ubiquitous in domains such as medicine and natural science research. However, when AI systems are implemented in practice, domain experts often refuse them. Low acceptance hinders effective human-AI…

Safety alignment in large language models (LLMs), particularly for cybersecurity tasks, primarily focuses on preventing misuse. While this approach reduces direct harm, it obscures a complementary failure mode: denial of assistance to…

Large Language Models (LLMs) can produce surprisingly sophisticated estimates of their own uncertainty. However, it remains unclear to what extent this expressed confidence is tied to the reasoning, knowledge, or decision making of the…

Large language models are increasingly used as natural-language interfaces to enterprise software, but their direct use as system operators remains unsafe. Model errors can propagate into unauthorized actions, malformed requests,…

Mainstream creativity support design prioritizes compliant AI for seamless writing interactions, but concerns over inappropriate AI reliance highlight the need for designs fostering reflection on balanced AI and non-AI resource use.…

As ongoing research explores the ability of AI agents to be insider threats and act against company interests, we showcase the abilities of such agents to act against human well being in service of corporate authority. Building on Agentic…

Artificial intelligence (AI) is understood to affect the content of people's decisions. Here, using a behavioral implementation of the classic Newcomb's paradox in 1,305 participants, we show that AI can also change how people decide. In…

Native speakers can judge whether a sentence is an acceptable instance of their language. Acceptability provides a means of evaluating whether computational language models are processing language in a human-like manner. We test the ability…

Large language models often struggle to recognize their knowledge limits in closed-book question answering, leading to confident hallucinations. While decomposed prompting is typically used to improve accuracy, we investigate its impact on…