8 papers · 1 filter
Debate with Images: Detecting Deceptive Behaviors in Multimodal Large Language Models
Sitong Fang, Shiyi Hou, Kaile Wang +6
Are frontier AI systems becoming more capable? Certainly. Yet such progress is not an unalloyed blessing but rather a Trojan horse: behind their performance leaps lie more insidiou…
InterMT: Multi-Turn Interleaved Preference Alignment with Human Feedback
Boyuan Chen, Donghai Hong, Jiaming Ji +12
As multimodal large models (MLLMs) continue to advance across challenging tasks, a key question emerges: What essential capabilities are still missing? A critical aspect of human l…
AI Deception: Risks, Dynamics, and Controls
Boyuan Chen, Sitong Fang, Jiaming Ji +56
As intelligence increases, so does its shadow. AI deception, in which systems induce false beliefs to secure self-beneficial outcomes, has evolved from a speculative concern to an…
PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human Preference
Jiaming Ji, Donghai Hong, Borong Zhang +10
In this study, we introduce the safety human preference dataset, PKU-SafeRLHF, designed to promote research on safety alignment in large language models (LLMs). As a sibling projec…
Mitigating Deceptive Alignment via Self-Monitoring
Jiaming Ji, Wenqi Chen, Kaile Wang +8
Modern large language models rely on chain-of-thought (CoT) reasoning to achieve impressive performance, yet the same mechanism can amplify deceptive alignment, situations in which…
Generative RLHF-V: Learning Principles from Multi-modal Human Preference
Jiayi Zhou, Jiaming Ji, Boyuan Chen +6
Training multi-modal large language models (MLLMs) that align with human intentions is a long-term challenge. Traditional score-only reward models for alignment suffer from low acc…