MAVEN: A Macro-Societal Value Evaluation Framework of Multimodal Content with Compact Aligned Evaluators
cs.CL, cs.LG
Submitted: 2026-06-08
Updated: 2026-10-29
Comments: 18 pages, 6 figures
Code: https://github.com/zzzzzzzzjj/MAVEN
Project page: https://tencent.github.io/llm.hunyuan.T1/README_EN.html
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Qwen3-VL Technical Report
- Qwen2.5-VL Technical Report
- Constitutional AI: Harmlessness from AI Feedback
- Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
- Aligning AI With Shared Human Values
- GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning
- GPT-4o System Card
- Safe RLHF-V: Safe Reinforcement Learning from Multi-modal Human Feedback
- Grading Scale Impact on LLM-as-a-Judge: Human-LLM Alignment Is Highest on 0-5 Grading Scale
- MORALISE: A Structured Benchmark for Moral Alignment in Visual Language Models
- HumaniBench: A Human-Centric Framework for Large Multimodal Models Evaluation
- Assessment of Multimodal Large Language Models in Alignment with Human Values
- OpenAI GPT-5 System Card
- Kimi-VL Technical Report
- Qwen3 Technical Report
- Multimodal RewardBench: Holistic Evaluation of Reward Models for Vision Language Models
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data