Modelling Human Values for AI Reasoning
The article discusses the importance of integrating human values into AI systems, a concept known as ‘value alignment’. Despite the growing body of research in this area, no formal model…
Continue readingHuman Values
Self-Alignment of Large Language Models via Monopolylogue-based Social Scene Simulation
This article discusses a novel method for aligning large language models (LLMs) with human values, using a social scene simulator called MATRIX. MATRIX emulates realistic social scenes based on user…
Continue readingLLM Self Defense: By Self Examination, LLMs Know They Are Being Tricked
Large Language Models (LLMs) have become an essential tool in generating high-quality text based on human prompts. However, they can potentially produce harmful content. This paper emphasizes the risk LLMs…
Continue reading Page 1 of 1