中文
相关论文

相关论文: Ethical Risk Analysis of L2 Rollups

200 篇论文

LLM safety and ethical alignment are widely discussed, but the impact of content moderation on user satisfaction remains underexplored. In particular, little is known about how users respond when models refuse to answer a prompt-one of the…

计算与语言 · 计算机科学 2025-05-19 Stefan Pasch

Many sets of ethics principles for responsible AI have been proposed to allay concerns about misuse and abuse of AI/ML systems. The underlying aspects of such sets of principles include privacy, accuracy, fairness, robustness,…

计算机与社会 · 计算机科学 2024-09-09 Conrad Sanderson , David Douglas , Qinghua Lu

The ethics of emerging technologies faces an anticipation dilemma: engaging too early risks overly speculative concerns, while engaging too late may forfeit the chance to shape a technology's trajectory. Despite various methods to address…

计算机与社会 · 计算机科学 2025-04-07 Eline de Jong

Experiments on online marketplaces and social networks suffer from interference, where the outcome of a unit is impacted by the treatment status of other units. We propose a framework for modeling interference using a ubiquitous deployment…

统计方法学 · 统计学 2023-08-21 Ariel Boyarsky , Hongseok Namkoong , Jean Pouget-Abadie

Leaderboard scores on public benchmarks have been steadily rising and converging, with many frontier language models now separated by only marginal differences. However, these scores often fail to match users' day to day experience, because…

人工智能 · 计算机科学 2026-02-05 Yiliang Song , Hongjun An , Jiangong Xiao , Haofei Zhao , Jiawei Shao , Xuelong Li

Ethical constraints on open-weight AI models are both a reflection of societal concerns and a foundation for AI governance policy. They are expected to propagate to downstream derivatives while implemented as voluntary metadata disclosures…

人工智能 · 计算机科学 2026-05-27 Weiwei Xu , Hengzhi Ye , Haoran Ye , Kai Gao , Vladimir Filkov , Minghui Zhou

The rapid advancements in large language models (LLMs) have revolutionized natural language processing, unlocking unprecedented capabilities in communication, automation, and knowledge generation. However, the ethical implications of LLM…

计算机与社会 · 计算机科学 2026-01-27 Javed I. Khan , Sharmila Rahman Prithula

Reproducibility problems that have long affected machine learning and reinforcement learning are now surfacing in agent research: papers compare systems by reported scores while leaving the rollout records behind those scores difficult to…

人工智能 · 计算机科学 2026-05-13 Charlie Masters , Ziyuan Liu , Stefano V. Albrecht

A risk in adopting third-party dependencies into an application is their potential to serve as a doorway for malicious code to be injected (most often unknowingly). While many initiatives from both industry and research communities focus on…

软件工程 · 计算机科学 2023-09-11 Supatsara Wattanakriengkrai , Raula Gaikovina Kula , Christoph Treude , Kenichi Matsumoto

Enterprise engagement with open source has evolved from tactical adoption to strategic deep integration, exposing them to a complex risk landscape far beyond mere code. However, traditional risk management, narrowly focused on technical…

软件工程 · 计算机科学 2025-11-03 Wenhao Yang , Minghui Zhou , Daniel Izquierdo Cortázar , Yehui Wang

Blockchains like Bitcoin and Ethereum have revolutionized digital transactions, yet scalability issues persist. Layer 2 solutions, such as validity proof Rollups (ZK-Rollups), aim to address these challenges by processing transactions…

密码学与安全 · 计算机科学 2025-09-16 Stefanos Chaliasos , Denis Firsov , Benjamin Livshits

Foundation models are powerful technologies: how they are released publicly directly shapes their societal impact. In this position paper, we focus on open foundation models, defined here as those with broadly available model weights (e.g.…

As the deployment of artificial intelligence (AI) is changing many fields and industries, there are concerns about AI systems making decisions and recommendations without adequately considering various ethical aspects, such as…

计算机与社会 · 计算机科学 2023-10-02 Conrad Sanderson , Qinghua Lu , David Douglas , Xiwei Xu , Liming Zhu , Jon Whittle

Developing high-stakes autonomous systems that include Artificial Intelligence (AI) components is complex; the consequences of errors can be catastrophic, yet it is challenging to plan for all operational cases. In stressful scenarios for…

人机交互 · 计算机科学 2025-12-04 Ben Larwood , Oliver J. Sutton , Callum Cockburn

Prominent AI companies are producing 'safety frameworks' as a type of voluntary self-governance. These statements purport to establish risk thresholds and safety procedures for the development and deployment of highly capable AI.…

计算机与社会 · 计算机科学 2025-10-14 Sam Coggins , Alexander K. Saeri , Katherine A. Daniell , Lorenn P. Ruster , Jessie Liu , Jenny L. Davis

Background: While Large Language Models (LLMs) have achieved widespread adoption, malicious prompt engineering specifically "jailbreak attacks" poses severe security risks by inducing models to bypass internal safety mechanisms. Current…

计算机与社会 · 计算机科学 2026-01-21 Chutian Huang , Dake Cao , Jiacheng Ji , Yunlou Fan , Chengze Yan , Hanhui Xu

Humans display significant uncertainty when confronted with moral dilemmas, yet the extent of such uncertainty in machines and AI agents remains underexplored. Recent studies have confirmed the overly confident tendencies of…

人工智能 · 计算机科学 2025-11-18 Jea Kwon , Luiz Felipe Vecchietti , Sungwon Park , Meeyoung Cha

AI-based systems can increasingly perform work tasks autonomously. In safety-critical tasks, human oversight of these systems is required to mitigate risks and to ensure responsibility in case something goes wrong. Since people often…

人机交互 · 计算机科学 2026-02-12 Cedric Faas , Richard Uth , Sarah Sterz , Markus Langer , Anna Maria Feit

Generative large language models present significant potential but also raise critical ethical concerns, including issues of safety, fairness, robustness, and reliability. Most existing ethical studies, however, are limited by their narrow…

计算与语言 · 计算机科学 2026-01-09 Yıldırım Özen , Burak Erinç Çetin , Kaan Engür , Elif Naz Demiryılmaz , Cagri Toraman

Large language models are increasingly influencing human moral decisions, yet current approaches focus primarily on evaluating rather than actively steering their moral decisions. We formulate this as an out-of-distribution moral alignment…

人工智能 · 计算机科学 2025-11-18 Zhiyu An , Wan Du