相关论文: Where Paths Split: Localized, Calibrated Control o…

Large language models are increasingly being used in critical domains of politics, business, and education, but the nature of their normative ethical judgment remains opaque. Alignment research has, to date, not sufficiently utilized…

Enhancing the moral alignment of Large Language Models (LLMs) is a critical challenge in AI safety. Current alignment techniques often act as superficial guardrails, leaving the intrinsic moral representations of LLMs largely untouched. In…

Ensuring that Large Language Models (LLMs) return just responses which adhere to societal values is crucial for their broader application. Prior research has shown that LLMs often fail to perform satisfactorily on tasks requiring moral…

Despite significant progress in alignment, large language models (LLMs) remain vulnerable to adversarial attacks that elicit harmful behaviors. Activation steering techniques offer a promising inference-time intervention approach, but…

Human moral judgment is context-dependent and modulated by interpersonal relationships. As large language models (LLMs) increasingly function as decision-support systems, determining whether they encode these social nuances is critical. We…

Large Language Models (LLMs) are known to acquire reasoning capabilities through shared inference patterns in pre-training data, which are further elicited via Chain-of-Thought (CoT) practices. However, whether fundamental reasoning…

Recent advances in Large Language Models (LLMs) highlight the need to align their behaviors with human values. A critical, yet understudied, issue is the potential divergence between an LLM's stated preferences (its reported alignment with…

With the rise and widespread use of Large Language Models (LLMs), ensuring their safety is crucial to prevent harm to humans and promote ethical behaviors. However, directly assessing value valence (i.e., support or oppose) by leveraging…

Inference-time computation has greatly enhanced the performance of large language models (LLMs) on challenging reasoning tasks, but this strategy can incur high inference costs. One solution is to route intermediate chain-of-thought (CoT)…

Pluralism alignment with AI has the sophisticated and necessary goal of creating AI that can coexist with and serve morally multifaceted humanity. Research towards pluralism alignment has many efforts in enhancing the learning of large…

Ethical reasoning is a crucial skill for Large Language Models (LLMs). However, moral values are not universal, but rather influenced by language and culture. This paper explores how three prominent LLMs -- GPT-4, ChatGPT, and…

LLM routing aims to select the most appropriate model for each query, balancing competing performance metrics such as accuracy and cost across a pool of language models. Prior approaches typically adopt a decoupled strategy, where the…

Moral norms vary across cultures. A recent line of work suggests that English large language models contain human-like moral biases, but these studies typically do not examine moral variation in a diverse cultural setting. We investigate…

Recent advances in Large Language Models (LLMs) have enabled human-like responses across various tasks, raising questions about their ethical decision-making capabilities and potential biases. This study systematically evaluates how nine…

The question of how to make decisions that maximise the well-being of all persons is very relevant to design language models that are beneficial to humanity and free from harm. We introduce the Greatest Good Benchmark to evaluate the moral…

Large Language Models (LLMs) are increasingly positioned as decision engines for hiring, healthcare, and economic judgment, yet real-world human judgment reflects a balance between rational deliberation and emotion-driven bias. If LLMs are…

The conceptual framework proposed in this paper centers on the development of a deliberative moral reasoning system - one designed to process complex moral situations by generating, filtering, and weighing normative arguments drawn from…

As large language models (LLMs) increasingly act as autonomous agents in markets and organizations, their behavior in strategic environments becomes economically consequential. We document that off-the-shelf LLM agents exhibit systematic…

Recent advancements in large language models (LLMs) have established them as powerful tools across numerous domains. However, persistent concerns about embedded biases, such as gender, racial, and cultural biases arising from their training…

People increasingly rely on Large Language Models (LLMs) for moral advice, which may influence humans' decisions. Yet, little is known about how closely LLMs align with human moral judgments. To address this, we introduce the Moral Dilemma…