Learning to Diagnose and Correct Moral Errors in Large Language Models
cs.CL
Submitted: 2026-01-06
Updated: 2026-11-05
Terminology
Sources
- Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
- Pragmatic Inference Chain (PIC) Improving LLMs' Reasoning of Authentic Implicit Toxic Language
- When Context Flips, Safety Breaks: Diagnosing Brittle Safety in Aligned Language Models
- The Capacity for Moral Self-Correction in Large Language Models
- The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning
- Pragmatic Inference for Improving Social Reasoning Generalization in Large Language Models
- Self-correction is Not An Innate Capability in Language Models
- Diagnosing Moral Reasoning Acquisition in Language Models: Pragmatics and Generalization
- GPT-4 Technical Report
- Safety Alignment Should Be Made More Than Just a Few Tokens Deep
- Llama 2: Open Foundation and Fine-Tuned Chat Models
- Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
- Deactivating Refusal Triggers: Understanding and Mitigating Overrefusal in Safety Alignment
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