相关论文: Assessing LLMs for Moral Value Pluralism

The advancement of large language models (LLMs) has outpaced traditional evaluation methodologies. This progress presents novel challenges, such as measuring human-like psychological constructs, moving beyond static and task-specific…

The application scope of Large Language Models (LLMs) continues to expand, leading to increasing interest in personalized LLMs that align with human values. However, aligning these models with individual values raises significant safety…

As large language models (LLMs) are increasingly used in human-centered tasks, assessing their psychological traits is crucial for understanding their social impact and ensuring trustworthy AI alignment. While existing reviews have covered…

For Large Language Models (LLMs), a disconnect persists between benchmark performance and real-world utility. Current evaluation frameworks remain fragmented, prioritizing technical metrics while neglecting holistic assessment for…

As large language models (LLMs) become more powerful and pervasive across society, ensuring these systems are beneficial, safe, and aligned with human values is crucial. Current alignment techniques, like Constitutional AI (CAI), involve…

With the rapid growth of Large Language Models (LLMs), criticism of their societal impact has also grown. Work in Responsible AI (RAI) has focused on the development of AI systems aimed at reducing harm. Responding to RAI's criticisms and…

Mainstream film is one of the richest sources of cultural content that AI systems learn from. Yet we have few tools for measuring the gender values it encodes. We present a proof-of-concept framework that turns fictional film characters…

Recent advances in large language models (LLMs) have enabled their use in complex agentic roles, involving decision-making with humans or other agents, making ethical alignment a key AI safety concern. While prior work has examined both…

Large language models (LLMs) have emerged as a powerful technology, and thus, we have seen widespread adoption and use on software engineering teams. Most often, LLMs are designed as "general purpose" technologies meant to represent the…

Reinforcement learning with verifiable rewards (RLVR) has achieved remarkable success in logical reasoning tasks, yet whether large language model (LLM) alignment requires fundamentally different approaches remains unclear. Given the…

LLMs have been demonstrated to align with the values of Western or North American cultures. Prior work predominantly showed this effect through leveraging surveys that directly ask (originally people and now also LLMs) about their values.…

Language embeds information about social, cultural, and political values people hold. Prior work has explored social and potentially harmful biases encoded in Pre-Trained Language models (PTLMs). However, there has been no systematic study…

Large language models implicitly encode preferences over human values, yet steering them often requires large training data. In this work, we investigate a simple approach: Can we reliably modify a model's value system in downstream…

Ensuring that Large Language Models (LLMs) align with mainstream human values and ethical norms is crucial for the safe and sustainable development of AI. Current value evaluation and alignment are constrained by Western cultural bias and…

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…

The emergence of Large Language Models (LLMs) has shifted language model evaluation toward reasoning and problem-solving tasks as measures of general intelligence. Small Language Models (SLMs) -- defined here as models under 10B parameters…

Large Language Models (LLMs) demonstrate a remarkable capacity to adopt different personas and roles; however, it remains unclear whether they can manifest behavior that adheres to a coherent, human-like value structure. In this work, we…

Evaluating natural language generation (NLG) systems remains a core challenge of natural language processing (NLP), further complicated by the rise of large language models (LLMs) that aims to be general-purpose. Recently, large language…

Large language models (LLMs) increasingly find their way into the most diverse areas of our everyday lives. They indirectly influence people's decisions or opinions through their daily use. Therefore, understanding how and which moral…

As intelligent systems become more autonomous, the scientific community focuses on creating decision-making mechanisms that include ethical and moral considerations, unlike traditional utility-maximisation models. To achieve this, a key…