paper-with-me

홈 › Papers

World Models: The Safety Perspective

2024-11-12 · Zifan Zeng, Chongzhe Zhang, Feng Liu, Joseph Sifakis, Qunli Zhang, Shiming Liu, Peng Wang

With the proliferation of the Large Language Model (LLM), the concept of World Models (WM) has recently attracted a great deal of attention in the AI research community, especially in the context of AI agents. It is arguably evolving into an essential foundation for building AI agent systems. A WM is intended to help the agent predict the future evolution of environmental states or help the agent fill in missing information so that it can plan its actions and behave safely. The safety property of WM plays a key role in their effective use in critical applications. In this work, we review and analyze the impacts of the current state-of-the-art in WM technology from the point of view of trustworthiness and safety based on a comprehensive survey and the fields of application envisaged. We provide an in-depth analysis of state-of-the-art WMs and derive technical research challenges and their impact in order to call on the research community to collaborate on improving the safety and trustworthiness of WM.

📄 PDF Abstract BibTeX arXiv:2411.07690

Code (0)

등록된 구현이 없습니다.

Tasks

AI AgentLanguage ModelingLanguage ModellingLarge Language Model

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음

Similar Papers 제목 키워드 기반

UnsafeBench: Benchmarking Image Safety Classifiers on Real-World and AI-Generated Images

2024-05-06 · Yiting Qu, Xinyue Shen, Yixin Wu, Michael Backes 외

With the advent of text-to-image models and concerns about their misuse, developers are increasingly relying on image safety classifiers to moderate their generated unsafe images. Yet, the performance of current image sa…

Benchmarking

Insights on Disagreement Patterns in Multimodal Safety Perception across Diverse Rater Groups

2024-10-22 · Charvi Rastogi, Tian Huey Teh, Pushkar Mishra, Roma Patel 외

AI systems crucially rely on human ratings, but these ratings are often aggregated, obscuring the inherent diversity of perspectives in real-world phenomenon. This is particularly concerning when evaluating the safety of…

Self-adaptive Dataset Construction for Real-World Multimodal Safety Scenarios

2025-09-04 · Jingen Qu, Lijun Li, Bo Zhang, Yichen Yan 외 arxiv

Multimodal large language models (MLLMs) are rapidly evolving, presenting increasingly complex safety challenges. However, current dataset construction methods, which are risk-oriented, fail to cover the growing complexi…

Trustworthy Reinforcement Learning Against Intrinsic Vulnerabilities: Robustness, Safety, and Generalizability

2022-09-16 · Mengdi Xu, Zuxin Liu, Peide Huang, Wenhao Ding 외

A trustworthy reinforcement learning algorithm should be competent in solving challenging real-world problems, including {robustly} handling uncertainties, satisfying {safety} constraints to avoid catastrophic failures, …

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

OmniCompliance-100K: A Multi-Domain, Rule-Grounded, Real-World Safety Compliance Dataset

2026-03-14 · Wenbin Hu, Huihao Jing, Haochen Shi, Changxuan Fan 외 arxiv

Ensuring the safety and compliance of large language models (LLMs) is of paramount importance. However, existing LLM safety datasets often rely on ad-hoc taxonomies for data generation and suffer from a significant short…