相关论文: Dropouts in Confidence: Moral Uncertainty in Human…

Large language models (LLMs) have emerged as powerful tools for addressing a wide range of general inquiries and tasks. Despite this, fine-tuning aligned LLMs on smaller, domain-specific datasets, critical to adapting them to specialized…

AI systems are increasingly tasked to complete responsibilities with decreasing oversight. This delegation requires users to accept certain risks, typically mitigated by perceived or actual alignment of values between humans and AI, leading…

In human society, trust is an essential component of social attitude that helps build and maintain long-term, healthy relationships which creates a strong foundation for cooperation, enabling individuals to work together effectively and…

Large Language Models (LLMs) push the bound-aries in natural language processing and generative AI, driving progress across various aspects of modern society. Unfortunately, the pervasive issue of bias in LLMs responses (i.e., predictions)…

Can LLMs accurately adjust their confidence when facing opposition? Building on previous studies measuring calibration on static fact-based question-answering tasks, we evaluate Large Language Models (LLMs) in a dynamic, adversarial debate…

Value alignment, which aims to ensure that large language models (LLMs) and other AI agents behave in accordance with human values, is critical for ensuring safety and trustworthiness of these systems. A key component of value alignment is…

Many sets of ethics principles for responsible AI have been proposed to allay concerns about misuse and abuse of AI/ML systems. The underlying aspects of such sets of principles include privacy, accuracy, fairness, robustness,…

Uncertainty quantification is essential for assessing the reliability and trustworthiness of modern AI systems. Among existing approaches, verbalized uncertainty, where models express their confidence through natural language, has emerged…

We build a custom transformer model to study how neural networks make moral decisions on trolley-style dilemmas. The model processes structured scenarios using embeddings that encode who is affected, how many people, and which outcome they…

The uncertainty measurement of classifiers' predictions is especially important in applications such as medical diagnoses that need to ensure limited human resources can focus on the most uncertain predictions returned by machine learning…

Large Language Models (LLMs) are increasingly tasked with creative generation, including the simulation of fictional characters. However, their ability to portray non-prosocial, antagonistic personas remains largely unexamined. We…

Selective prediction systems can mitigate harms resulting from language model hallucinations by abstaining from answering in high-risk cases. Uncertainty quantification techniques are often employed to identify such cases, but are rarely…

Critical decision-making in socially consequential spaces is increasingly involving AI systems at varying capacities. Yet, despite the ubiquity of autonomous systems, most approaches to handling autonomous moral decision-making resort to…

The capabilities of artificial intelligence systems have been advancing to a great extent, but these systems still struggle with failure modes, vulnerabilities, and biases. In this paper, we study the current state of the field, and present…

Autonomous systems increasingly require moral judgment capabilities, yet whether these capabilities scale predictably with model size remains unexplored. We systematically evaluate 75 large language model configurations (0.27B--1000B…

Human commonsense understanding of the physical and social world is organized around intuitive theories. These theories support making causal and moral judgments. When something bad happens, we naturally ask: who did what, and why? A rich…

How do Large Language Models understand moral dimensions compared to humans? This first large-scale Bayesian evaluation of market-leading language models provides the answer. In contrast to prior work using deterministic ground truth…

Large language models (LLMs) are increasingly used in decision-making contexts, but when they present answers without signaling low confidence, users may unknowingly act on erroneous outputs. Prior work shows that LLMs maintain internal…

Recently, computer scientists have developed large language models (LLMs) by training prediction models with large-scale language corpora and human reinforcements. The LLMs have become one promising way to implement artificial intelligence…

Understanding why a large language model (LLM) is uncertain about the response is important for their reliable deployment. Current approaches, which either provide a single uncertainty score or rely on the classical aleatoric-epistemic…