Cat-DPO: Category-Adaptive Safety Alignment
cs.CL, cs.AI
Submitted: 2026-04-19
Updated: 2026-11-07
Code: https://github.com/paul-rottger/xstest
Terminology
Sources
- A Personalized Conversational Benchmark: Towards Simulating Personalized Conversations
- No Attacker Needed: Unintentional Cross-User Contamination in Shared-State LLM Agents
- Auditable Agents
- Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
- Direct Preference Optimization with Unobserved Preference Heterogeneity: The Necessity of Ternary Preferences
- Fine-Tuning Language Models from Human Preferences
- Llama 2: Open Foundation and Fine-Tuned Chat Models
- Qwen3 Technical Report
- GPT-4o System Card
- From Hard Refusals to Safe-Completions: Toward Output-Centric Safety Training
- Proximal Policy Optimization Algorithms
- Margin Adaptive DPO: Leveraging Reward Model for Granular Control in Preference Optimization
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