Reading the Room: Foundations, Design, and Challenges of Normative Competence in LLMs
cs.AI, cs.MA
Submitted: 2026-10-07
Updated: 2026-10-12
Project page: https://andreawynn.github.io/1
Sources
- Constitutional AI: Harmlessness from AI Feedback
- Contrastive Chain-of-Thought Prompting
- Improving Factuality and Reasoning in Language Models through Multiagent Debate
- Moral Stories: Situated Reasoning about Norms, Intents, Actions, and their Consequences
- Legible Normativity for AI Alignment: The Value of Silly Rules
- Personalisation within bounds: A risk taxonomy and policy framework for the alignment of large language models with personalised feedback
- The PRISM Alignment Dataset: What Participatory, Representative and Individualised Human Feedback Reveals About the Subjective and Multicultural Alignment of Large Language Models
- A Theory of Appropriateness That Accounts for Norms of Rationality
- CultureLLM: Incorporating Cultural Differences into Large Language Models
- Theory of Mind for Multi-Agent Collaboration via Large Language Models
- Training language models to follow instructions with human feedback
- Large Pre-trained Language Models Contain Human-like Biases of What is Right and Wrong to Do
- Multiagent Finetuning: Self Improvement with Diverse Reasoning Chains
- MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark
- Talk Isn't Always Cheap: Understanding Failure Modes in Multi-Agent Debate
- Controlling the Risk of Corrupted Contexts for Language Models via Early-Exiting
- Instruction-Following Evaluation for Large Language Models
- Few-shot Language Coordination by Modeling Theory of Mind
- Fine-Tuning Language Models from Human Preferences
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
- Agents' Last Exam
- 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