On the Context Sensitivity of LLM Moral Judgment
cs.AI, cs.CL, cs.CY, cs.HC
Submitted: 2026-03-24
Updated: 2026-09-08
Comments: EMNLP 2026
Code: https://github.com/adrian-sauter/contextual_moralchoice
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Moral Foundations of Large Language Models
- GPT-4 Technical Report
- Deep Value Benchmark: Measuring Whether Models Generalize Deep Values or Shallow Preferences
- Qwen Technical Report
- Constitutional AI: Harmlessness from AI Feedback
- Inducing anxiety in large language models can induce bias
- Mechanistic Interpretability for AI Safety -- A Review
- DeepSeek LLM: Scaling Open-Source Language Models with Longtermism
- Taken out of context: On measuring situational awareness in LLMs
- DeepSeek-V3 Technical Report
- SaGE: Evaluating Moral Consistency in Large Language Models
- LoRA: Low-Rank Adaptation of Large Language Models
- GPT-4o System Card
- Alignment faking in large language models
- Mistral 7B
- Mixtral of Experts
- Can Machines Learn Morality? The Delphi Experiment
- Discerning What Matters: A Multi-Dimensional Assessment of Moral Competence in LLMs
- TextBugger: Generating Adversarial Text Against Real-world Applications
- The Linear Representation Hypothesis and the Geometry of Large Language Models
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection