English
Related papers

Related papers: Keep Calm and Avoid Harmful Content: Concept Align…

200 papers

We study the problem of controlling the difficulty level of text generated by Large Language Models (LLMs) for contexts where end-users are not fully proficient, such as language learners. Using a novel framework, we evaluate the…

Computation and Language · Computer Science 2024-06-06 Ali Malik , Stephen Mayhew , Chris Piech , Klinton Bicknell

We investigate whether Large Language Models (LLMs) exhibit human-like cognitive patterns under four established frameworks from psychology: Thematic Apperception Test (TAT), Framing Bias, Moral Foundations Theory (MFT), and Cognitive…

Artificial Intelligence · Computer Science 2025-12-12 Akash Kundu , Rishika Goswami

As Large Language Models (LLMs) become ubiquitous, the challenge of securing them against adversarial "jailbreaking" attacks has intensified. Current defense strategies often rely on computationally expensive external classifiers or brittle…

Machine Learning · Computer Science 2025-12-17 Md. Hasib Ur Rahman

Harmful fine-tuning attack introduces significant security risks to the fine-tuning services. Main-stream defenses aim to vaccinate the model such that the later harmful fine-tuning attack is less effective. However, our evaluation results…

Computation and Language · Computer Science 2026-01-19 Yibo Wang , Tiansheng Huang , Li Shen , Huanjin Yao , Haotian Luo , Rui Liu , Naiqiang Tan , Jiaxing Huang , Dacheng Tao

Large Language Models (LLMs) are typically harmless but remain vulnerable to carefully crafted prompts known as ``jailbreaks'', which can bypass protective measures and induce harmful behavior. Recent advancements in LLMs have incorporated…

Cryptography and Security · Computer Science 2024-06-03 Haibo Jin , Andy Zhou , Joe D. Menke , Haohan Wang

Hallucination, the generation of factually incorrect content, is a growing challenge in Large Language Models (LLMs). Existing detection and mitigation methods are often isolated and insufficient for domain-specific needs, lacking a…

Computation and Language · Computer Science 2025-01-22 Mengfei Liang , Archish Arun , Zekun Wu , Cristian Munoz , Jonathan Lutch , Emre Kazim , Adriano Koshiyama , Philip Treleaven

Although large language models (LLMs) have achieved remarkable advancements, their security remains a pressing concern. One major threat is jailbreak attacks, where adversarial prompts bypass model safeguards to generate harmful or…

Cryptography and Security · Computer Science 2025-05-21 Tiehan Cui , Yanxu Mao , Peipei Liu , Congying Liu , Datao You

Social media platforms utilize Machine Learning (ML) and Artificial Intelligence (AI) powered recommendation algorithms to maximize user engagement, which can result in inadvertent exposure to harmful content. Current moderation efforts,…

Computation and Language · Computer Science 2025-05-30 Rajvardhan Oak , Muhammad Haroon , Claire Jo , Magdalena Wojcieszak , Anshuman Chhabra

Low-altitude wireless networks (LAWNs) have the potential to revolutionize communications by supporting a range of applications, including urban parcel delivery, aerial inspections and air taxis. However, compared with traditional wireless…

Networking and Internet Architecture · Computer Science 2026-01-21 Chuang Zhang , Geng Sun , Yijing Lin , Weijie Yuan , Sinem Coleri , Dusit Niyato

We propose a new approach to promote safety in classification tasks with established concepts. Our approach -- called a conceptual safeguard -- acts as a verification layer for models that predict a target outcome by first predicting the…

Machine Learning · Computer Science 2024-11-08 Hailey Joren , Charles Marx , Berk Ustun

Mitigating hallucinations in Large Language Models (LLMs) is critical for their reliable deployment. Existing methods typically fine-tune LLMs to abstain from answering questions beyond their knowledge scope. However, these methods often…

Computation and Language · Computer Science 2025-10-29 Hao An , Yang Xu

Concept Bottleneck Models (CBMs) aim to deliver interpretable predictions by routing decisions through a human-understandable concept layer, yet they often suffer reduced accuracy and concept leakage that undermines faithfulness. We…

Machine Learning · Computer Science 2026-02-17 Karim Galliamov , Syed M Ahsan Kazmi , Adil Khan , Adín Ramírez Rivera

While explicit Chain-of-Thought (CoT) equips Large Language Models (LLMs) with strong reasoning capabilities, it requires models to verbalize every intermediate step in text tokens, constraining the model thoughts to the discrete vocabulary…

Computation and Language · Computer Science 2026-02-12 Weihao Liu , Dehai Min , Lu Cheng

Though safety alignment has been applied to most large language models (LLMs), LLM service providers generally deploy a subsequent moderation as the external safety guardrail in real-world products. Existing moderators mainly practice a…

Computation and Language · Computer Science 2025-09-23 Yang Li , Qiang Sheng , Yehan Yang , Xueyao Zhang , Juan Cao

The increased presence of large language models (LLMs) in educational settings has ignited debates concerning negative repercussions, including overreliance and inadequate task reflection. Our work advocates moderated usage of such models,…

While the wide adoption of refusal training in large language models (LLMs) has showcased improvements in model safety, recent works have highlighted shortcomings due to the shallow nature of these alignment methods. To this end, the work…

Machine Learning · Computer Science 2026-04-17 Pankayaraj Pathmanathan , Furong Huang

Large reasoning models (LRMs) "think" by generating structured chain-of-thought (CoT) before producing a final answer, yet they still lack the ability to reason critically about safety alignment and are easily biased when a flawed premise…

Our intention is to provide a definitive reference on what it would take to safely make use of generative/predictive models in the absence of a solution to the Eliciting Latent Knowledge problem. Furthermore, we believe that large language…

Artificial Intelligence · Computer Science 2023-02-07 Evan Hubinger , Adam Jermyn , Johannes Treutlein , Rubi Hudson , Kate Woolverton

Recent advancements in Large Language Models (LLMs) have sparked widespread concerns about their safety. Recent work demonstrates that safety alignment of LLMs can be easily removed by fine-tuning with a few adversarially chosen…

Computation and Language · Computer Science 2025-03-03 Samuele Poppi , Zheng-Xin Yong , Yifei He , Bobbie Chern , Han Zhao , Aobo Yang , Jianfeng Chi

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…