中文
相关论文

相关论文: CR4T: Rewrite-Based Guardrails for Adolescent LLM …

200 篇论文

Guardrail, an emerging mechanism designed to ensure that large language models (LLMs) align with human values by moderating harmful or toxic responses, requires a sociotechnical approach in their design. This paper addresses a critical…

人工智能 · 计算机科学 2025-06-05 Jinwei Hu , Yi Dong , Xiaowei Huang

Safety guardrails in large language models(LLMs) are developed to prevent malicious users from generating toxic content at a large scale. However, these measures can inadvertently introduce or reflect new biases, as LLMs may refuse to…

计算与语言 · 计算机科学 2025-11-03 Adel Khorramrouz , Sharon Levy

Recent advancements in Large Language Models (LLMs) have showcased remarkable capabilities across various tasks in different domains. However, the emergence of biases and the potential for generating harmful content in LLMs, particularly…

密码学与安全 · 计算机科学 2024-07-25 Zhuowen Yuan , Zidi Xiong , Yi Zeng , Ning Yu , Ruoxi Jia , Dawn Song , Bo Li

The AI era has ushered in Large Language Models (LLM) to the technological forefront, which has been much of the talk in 2023, and is likely to remain as such for many years to come. LLMs are the AI models that are the power house behind…

密码学与安全 · 计算机科学 2026-01-22 Anjanava Biswas , Wrick Talukdar

The rapid proliferation of large language models (LLMs) in applications targeting children and adolescents necessitates a fundamental reassessment of prevailing AI safety frameworks, which are largely tailored to adult users and neglect the…

计算与语言 · 计算机科学 2025-12-16 Wenpeng Xing , Lanyi Wei , Haixiao Hu , Jingyi Yu , Rongchang Li , Mohan Li , Changting Lin , Meng Han

Large Language Models (LLMs) are vulnerable to jailbreak attacks that exploit weaknesses in traditional safety alignment, which often relies on rigid refusal heuristics or representation engineering to block harmful outputs. While they are…

计算与语言 · 计算机科学 2025-10-01 Yuyou Zhang , Miao Li , William Han , Yihang Yao , Zhepeng Cen , Ding Zhao

Large Language Models (LLMs) have demonstrated powerful capabilities that render them valuable in different applications, including conversational AI products. It is paramount to ensure the security and reliability of these products by…

计算与语言 · 计算机科学 2025-01-23 Melissa Kazemi Rad , Huy Nghiem , Andy Luo , Sahil Wadhwa , Mohammad Sorower , Stephen Rawls

Large Language Models (LLMs) are rapidly entering children's lives - through parent-driven adoption, schools, and peer networks - yet current AI ethics and safety research do not adequately address content-related risks specific to minors.…

计算与语言 · 计算机科学 2025-03-14 Shaun Khoo , Gabriel Chua , Rachel Shong

Achieving robust safety alignment in large language models (LLMs) while preserving their utility remains a fundamental challenge. Existing approaches often struggle to balance comprehensive safety with fine-grained controllability at the…

人工智能 · 计算机科学 2025-09-25 Huizhen Shu , Xuying Li , Zhuo Li

As Large Language Models (LLMs) increasingly power applications used by children and adolescents, ensuring safe and age-appropriate interactions has become an urgent ethical imperative. Despite progress in AI safety, current evaluations…

计算机与社会 · 计算机科学 2026-05-26 Junfeng Jiao , Saleh Afroogh , Kevin Chen , Abhejay Murali , David Atkinson , Amit Dhurandhar

Large Language Models (LLMs) are increasingly embedded in child-facing contexts such as education, companionship, creative tools, but their deployment raises safety, privacy, developmental, and security risks. We conduct a systematic…

计算机与社会 · 计算机科学 2026-05-26 Junfeng Jiao , Saleh Afroogh , Kevin Chen , Abhejay Murali , David Atkinson , Amit Dhurandhar

Large Language Models (LLMs) are increasingly used by teenagers and young adults in everyday life, ranging from emotional support and creative expression to educational assistance. However, their unique vulnerabilities and risk profiles…

人机交互 · 计算机科学 2025-09-12 Yaman Yu , Yiren Liu , Jacky Zhang , Yun Huang , Yang Wang

Safety alignment in large language models (LLMs) is primarily evaluated under open-ended generation, where models can mitigate risk by refusing to respond. In contrast, many real-world applications place LLMs in structured decision-making…

计算与语言 · 计算机科学 2026-04-21 Yuheng Chen , Zhiyu Wu , Bowen Cheng , Tetsuro Takahashi

Large Language Models (LLM) have made remarkable progress, but concerns about potential biases and harmful content persist. To address these apprehensions, we introduce a practical solution for ensuring LLM's safe and ethical use. Our novel…

密码学与安全 · 计算机科学 2025-04-24 Chaima Njeh , Haïfa Nakouri , Fehmi Jaafar

Large Language Models (LLMs) are widely deployed in diverse real-world settings, yet remain vulnerable to jailbreaking, where prompt-based attacks bypass safety filters. We present THREAT (Targeted Harmful generation via Reframing and…

密码学与安全 · 计算机科学 2026-05-22 Shahnewaz Karim Sakib , Swati Kar , Anindya Bijoy Das

Generative AI systems are increasingly assisting and acting on behalf of end users in practical settings, from digital shopping assistants to next-generation autonomous cars. In this context, safety is no longer about blocking harmful…

人工智能 · 计算机科学 2026-05-20 Ravi Pandya , Madison Bland , Duy P. Nguyen , Changliu Liu , Jaime Fernández Fisac , Andrea Bajcsy

With the increasing adoption of large language models (LLMs), ensuring the safety of LLM systems has become a pressing concern. External LLM-based guardrail models have emerged as a popular solution to screen unsafe inputs and outputs, but…

Large language models (LLMs) have demonstrated remarkable capabilities across various tasks, but ensuring their safety and alignment with human values remains crucial. Current safety alignment methods, such as supervised fine-tuning and…

计算与语言 · 计算机科学 2025-03-13 Bilgehan Sel , Dingcheng Li , Phillip Wallis , Vaishakh Keshava , Ming Jin , Siddhartha Reddy Jonnalagadda

As large language models (LLMs) are increasingly deployed in high-stakes settings, the risk of generating harmful or toxic content remains a central challenge. Post-hoc alignment methods are brittle: once unsafe patterns are learned during…

Large Language Models (LLMs) remain susceptible to jailbreak exploits that bypass safety filters and induce harmful or unethical behavior. This work presents a systematic taxonomy of existing jailbreak defenses across prompt-level,…

密码学与安全 · 计算机科学 2025-11-25 Ryan Wong , Hosea David Yu Fei Ng , Dhananjai Sharma , Glenn Jun Jie Ng , Kavishvaran Srinivasan
‹ 上一页 1 2 3 10 下一页 ›