Value fulcra: Mapping large language models to the multidimensional spectrum of basic human values

[PDF] arxiv.org

Sora: A review on background, technology, limitations, and opportunities of large vision models

Y Liu, K Zhang, Y Li, Z Yan, C Gao, R Chen… - arXiv preprint arXiv …, 2024 - arxiv.org
Sora is a text-to-video generative AI model, released by OpenAI in February 2024. The
model is trained to generate videos of realistic or imaginative scenes from text instructions …
被引用次数：55 相关文章 所有 2 个版本
[PDF] arxiv.org

I Think, Therefore I am: Awareness in Large Language Models

Y Li, Y Huang, Y Lin, S Wu, Y Wan, L Sun - arXiv preprint arXiv …, 2024 - arxiv.org
Do large language models (LLMs) exhibit any forms of awareness similar to humans? In this
paper, we introduce the concept of awareness to LLMs, arguing that awareness is an …
被引用次数：2 相关文章 所有 2 个版本
[PDF] arxiv.org

From Sora What We Can See: A Survey of Text-to-Video Generation

R Sun, Y Zhang, T Shah, J Sun, S Zhang, W Li… - arXiv preprint arXiv …, 2024 - arxiv.org
With impressive achievements made, artificial intelligence is on the path forward to artificial
general intelligence. Sora, developed by OpenAI, which is capable of minute-level world …
相关文章 所有 3 个版本
[PDF] arxiv.org

Prototypical Reward Network for Data-Efficient RLHF

J Zhang, X Wang, Y Jin, C Chen, X Zhang… - arXiv preprint arXiv …, 2024 - arxiv.org
The reward model for Reinforcement Learning from Human Feedback (RLHF) has proven
effective in fine-tuning Large Language Models (LLMs). Notably, collecting human feedback …
被引用次数：1 相关文章 所有 2 个版本
[PDF] arxiv.org

Beyond Human Norms: Unveiling Unique Values of Large Language Models through Interdisciplinary Approaches

P Biedma, X Yi, L Huang, M Sun, X Xie - arXiv preprint arXiv:2404.12744, 2024 - arxiv.org
Recent advancements in Large Language Models (LLMs) have revolutionized the AI field
but also pose potential safety and ethical risks. Deciphering LLMs' embedded values …
相关文章 所有 2 个版本
[PDF] arxiv.org

ValueBench: Towards Comprehensively Evaluating Value Orientations and Understanding of Large Language Models

Y Ren, H Ye, H Fang, X Zhang, G Song - arXiv preprint arXiv:2406.04214, 2024 - arxiv.org
Large Language Models (LLMs) are transforming diverse fields and gaining increasing
influence as human proxies. This development underscores the urgent need for evaluating …
相关文章 所有 2 个版本
[PDF] arxiv.org

Modular Pluralism: Pluralistic Alignment via Multi-LLM Collaboration

S Feng, T Sorensen, Y Liu, J Fisher, CY Park… - arXiv preprint arXiv …, 2024 - arxiv.org
While existing alignment paradigms have been integral in developing large language
models (LLMs), LLMs often learn an averaged human preference and struggle to model …
相关文章 所有 2 个版本
[PDF] arxiv.org

Quantifying Misalignment Between Agents

A Kierans, A Ghosh, H Hazan… - arXiv preprint arXiv …, 2024 - arxiv.org
Growing concerns about the AI alignment problem have emerged in recent years, with
previous work focusing mainly on (1) qualitative descriptions of the alignment problem;(2) …
被引用次数：2 相关文章 所有 6 个版本
[PDF] westscience-press.com

Bibliometric Analysis of Social Protection Programs in Social Welfare

L Judijanto, MA Muhtadi… - West Science Social …, 2024 - wsj.westscience-press.com
This bibliometric analysis examines the scholarly discourse surrounding social protection
programs in the domain of social welfare. With a focus on understanding the landscape …
相关文章