相关论文: Value FULCRA: Mapping Large Language Models to the…

The rapid development and deployment of large language models (LLMs) have introduced a new frontier in artificial intelligence, marked by unprecedented capabilities in natural language understanding and generation. However, the increasing…

As large language models (LLMs) are employed worldwide, existing evaluation paradigms for their multilingual capabilities primarily focus on factual task performance, neglecting the ability to judge content's deep-level values across…

Social alignment in AI systems aims to ensure that these models behave according to established societal values. However, unlike humans, who derive consensus on value judgments through social interaction, current language models (LMs) are…

Personal values are a crucial factor behind human decision-making. Considering that Large Language Models (LLMs) have been shown to impact human decisions significantly, it is essential to make sure they accurately understand human values…

Honesty is a fundamental principle for aligning large language models (LLMs) with human values, requiring these models to recognize what they know and don't know and be able to faithfully express their knowledge. Despite promising, current…

Large Language Models (LLMs) are increasingly used in decision-making scenarios that involve risk assessment, yet their alignment with human economic rationality remains unclear. In this study, we investigate whether LLMs exhibit risk…

The rapid progress in Large Language Models (LLMs) poses potential risks such as generating unethical content. Assessing LLMs' values can help expose their misalignment, but relies on reference-free evaluators, e.g., fine-tuned LLMs or…

Conversational human-likeness plays a central role in human-AI interaction, yet it has remained difficult to define, measure, and optimize. As a result, improvements in human-like behavior are largely driven by scale or broad supervised…

Large language models (LLMs) can underpin AI assistants that help users with everyday tasks, such as by making recommendations or performing basic computation. Despite AI assistants' promise, little is known about the implicit values these…

Large language models (LLMs) closely interact with humans, and thus need an intimate understanding of the cultural values of human society. In this paper, we explore how open-source LLMs make judgments on diverse categories of cultural…

The rapid progress in Large Language Models (LLMs) could transform many fields, but their fast development creates significant challenges for oversight, ethical creation, and building user trust. This comprehensive review looks at key trust…

The rapid evolution of Large Language Models (LLMs) highlights the necessity for ethical considerations and data integrity in AI development, particularly emphasizing the role of FAIR (Findable, Accessible, Interoperable, Reusable) data…

Large language models (LLMs) can lead to undesired consequences when misaligned with human values, especially in scenarios involving complex and sensitive social biases. Previous studies have revealed the misalignment of LLMs with human…

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…

Moral values have deep roots in early civilizations, codified within norms and laws that regulated societal order and the common good. They play a crucial role in understanding the psychological basis of human behavior and cultural…

One of today's most significant societal challenges is building AI systems whose behaviour, or the behaviour it enables within communities of interacting agents (human and artificial), aligns with human values. To address this challenge, we…

Big models have greatly advanced AI's ability to understand, generate, and manipulate information and content, enabling numerous applications. However, as these models become increasingly integrated into everyday life, their inherent…

Generative artificial intelligence (AI) systems based on large-scale pretrained foundation models (PFMs) such as vision-language models, large language models (LLMs), diffusion models and vision-language-action (VLA) models have…

Large language models (LLMs) have demonstrated remarkable capabilities but often struggle to align with human preferences, leading to harmful or undesirable outputs. Preference learning, which trains models to distinguish between preferred…

With generative artificial intelligence (AI), particularly large language models (LLMs), continuing to make inroads in healthcare, it is critical to supplement traditional automated evaluations with human evaluations. Understanding and…