#Prompt Engineering
Latest news articles tagged with "Prompt Engineering". Follow the timeline of events, related topics, and entities.
Articles (8)
-
🇺🇸 Analysis of LLMs Against Prompt Injection and Jailbreak Attacks
[USA]
arXiv:2602.22242v1 Announce Type: cross Abstract: Large Language Models (LLMs) are widely deployed in real-world systems. Given their broader applicability, prompt engineering has become an efficient...
Related: #AI Security, #Vulnerability Assessment -
🇺🇸 Scaling In, Not Up? Testing Thick Citation Context Analysis with GPT-5 and Fragile Prompts
[USA]
arXiv:2602.22359v1 Announce Type: cross Abstract: This paper tests whether large language models (LLMs) can support interpretative citation context analysis (CCA) by scaling in thick, text-grounded r...
Related: #Artificial Intelligence, #Academic Research, #Citation Analysis -
🇺🇸 Say It My Way: Exploring Control in Conversational Visual Question Answering with Blind Users
[USA]
arXiv:2602.16930v1 Announce Type: cross Abstract: Prompting and steering techniques are well established in general-purpose generative AI, yet assistive visual question answering (VQA) tools for blin...
Related: #Accessibility for Blind Users, #Conversational Visual Question Answering, #Human‑Computer Interaction (HCI), #User Control and Customization -
🇺🇸 From Subtle to Significant: Prompt-Driven Self-Improving Optimization in Test-Time Graph OOD Detection
[USA]
arXiv:2602.17342v1 Announce Type: cross Abstract: Graph Out-of-Distribution (OOD) detection aims to identify whether a test graph deviates from the distribution of graphs observed during training, wh...
Related: #Graph Neural Networks, #Out‑of‑Distribution Detection, #Test‑Time Training, #Self‑Improving / Iterative Learning -
🇺🇸 Defining and Evaluating Physical Safety for Large Language Models
[USA]
arXiv:2411.02317v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are increasingly used to control robotic systems such as drones, but their risks of causing physical threats and...
Related: #Large Language Model Safety, #Robotic System Control, #Benchmark Development, #Regulatory Compliance -
🇺🇸 PERSONA: Dynamic and Compositional Inference-Time Personality Control via Activation Vector Algebra
[USA]
arXiv:2602.15669v1 Announce Type: new Abstract: Current methods for personality control in Large Language Models rely on static prompting or expensive fine-tuning, failing to capture the dynamic and ...
Related: #Large Language Models, #Personalization in AI, #Dynamic Inference, #Human–Computer Interaction -
🇺🇸 ProMoral-Bench: Evaluating Prompting Strategies for Moral Reasoning and Safety in LLMs
[USA]
arXiv:2602.13274v1 Announce Type: new Abstract: Prompt design significantly impacts the moral competence and safety alignment of large language models (LLMs), yet empirical comparisons remain fragmen...
Related: #Artificial Intelligence Ethics, #Natural Language Processing Evaluation, #Robustness Testing in LLMs, #Model Safety & Alignment -
🇺🇸 String Seed of Thought: Prompting LLMs for Distribution-Faithful and Diverse Generation
[USA]
arXiv:2510.21150v3 Announce Type: replace Abstract: We introduce String Seed of Thought (SSoT), a novel prompting method for LLMs that improves Probabilistic Instruction Following (PIF). We define PI...
Related: #Artificial Intelligence, #Machine Learning