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

Would artificial intelligence (AI) cut interest rates or adopt conservative monetary policy? Would it deregulate or opt for a more controlled economy? As AI use by economic policymakers, academics, and market participants grows…

Imitation learning algorithms provide state-of-the-art results on many structured prediction tasks by learning near-optimal search policies. Such algorithms assume training-time access to an expert that can provide the optimal action at any…

Large Language Models (LLMs) exhibit surprisingly diverse risk preferences when acting as AI decision makers, a crucial characteristic whose origins remain poorly understood despite their expanding economic roles. We analyze 50 LLMs using…

Existing benchmarks of language-model refusal on malicious-coding tasks routinely conflate requests for executable malicious software with requests for harmful security knowledge. This conflation matters because the two request types…

We investigate whether Large Language Models (LLMs) exhibit altruistic tendencies, and critically, whether their implicit associations and self-reports predict actual altruistic behavior. Using a multi-method approach inspired by human…

Recent advances in AI models have increased the integration of AI-based decision aids into the human decision making process. To fully unlock the potential of AI-assisted decision making, researchers have computationally modeled how humans…

As Large Language Models become ubiquitous sources of health information, understanding their capacity to accurately represent stigmatized conditions is crucial for responsible deployment. This study examines whether leading AI systems…

Why do language models trained on contradictory data prefer correct answers? In controlled experiments with small transformers (3.5M--86M parameters), we show that this preference tracks the compressibility structure of errors rather than…

Ambiguity is an intrinsic feature of natural language. Managing ambiguity is a key part of human language understanding, allowing us to anticipate misunderstanding as communicators and revise our interpretations as listeners. As language…

Access control is a cornerstone of secure computing, yet large language models often blur role boundaries by producing unrestricted responses. We study role-conditioned refusals, focusing on the LLM's ability to adhere to access control…

Foundation models excel in stable environments, yet often fail where reliability matters most: medicine, finance, and policy. This Fidelity Paradox is not just a data problem; it is structural. In domains where rules change over time, extra…

Large Language Models based on transformer algorithms have revolutionized Artificial Intelligence by enabling verbal interaction with machines akin to human conversation. These AI agents have surpassed the Turing Test, achieving confusion…

Artificial Intelligence (AI) is taking on increasingly autonomous roles, e.g., browsing the web as a research assistant and managing money. But specifying goals and restrictions for AI behavior is difficult. Similar to how parties to a…

Prior work argues that refusal in large language models is mediated by a single activation-space direction, enabling effective steering and ablation. We show that this account is incomplete. Across eleven categories of refusal and…

Post-training alignment optimizes language models to match human preference signals, but this objective is not equivalent to modeling observed human behavior. We compare 120 base-aligned model pairs on more than 10,000 real human decisions…

Large language models are able to perform a task by conditioning on a few input-output demonstrations - a paradigm known as in-context learning. We show that language models can explicitly infer an underlying task from a few demonstrations…

Large language models (LLMs) are typically aligned to refuse harmful instructions through safety fine-tuning. A recent attack, termed abliteration, identifies and suppresses the single latent direction most responsible for refusal behavior,…

As large language models (LLMs) are increasingly used for work, personal, and therapeutic purposes, researchers have begun to investigate these models' implicit and explicit moral views. Previous work, however, focuses on asking LLMs to…

The application of machine learning based decision making systems in safety critical areas requires reliable high certainty predictions. Reject options are a common way of ensuring a sufficiently high certainty of predictions made by the…

The deployment of Large Language Models (LLMs) as tool-using agents causes their alignment training to manifest in new ways. Recent work finds that language models can use tools in ways that contradict the interests or explicit instructions…