# ConstitutionalExperts: Training a Mixture of Principle-based Prompts

arXiv: https://arxiv.org/abs/2403.04894 · HTML: https://mlsanity.com/paper/2403.04894/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Placed in MoE large language models, one of 12 directions in Mixture-of-experts.
- Builds on 18 of its 28 references that are in the map.
- First posted on arXiv 7 Mar 2024.

## Placed in

- Mixture-of-experts / [MoE large language models](https://mlsanity.com/moe/moe-large-language-models/)

## Builds on (most cited first, 18 of 18)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [Sparks of Artificial General Intelligence: Early experiments with GPT-4](https://mlsanity.com/paper/2303.12712/) (2023)
- [Large Language Models are not Fair Evaluators](https://mlsanity.com/paper/2305.17926/) (2023)
- [Automatic Prompt Optimization with "Gradient Descent" and Beam Search](https://mlsanity.com/paper/2305.03495/) (2023)
- [Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution](https://mlsanity.com/paper/2309.16797/) (2023)
- [Learning How to Ask: Querying LMs with Mixtures of Soft Prompts](https://mlsanity.com/paper/2104.06599/) (2021)
- [RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learning](https://mlsanity.com/paper/2205.12548/) (2022)
- ["Liar, Liar Pants on Fire": A New Benchmark Dataset for Fake News Detection](https://mlsanity.com/paper/1705.00648/) (2017)
- [A Holistic Approach to Undesired Content Detection in the Real World](https://mlsanity.com/paper/2208.03274/) (2022)
- [Can Generalist Foundation Models Outcompete Special-Purpose Tuning? Case Study in Medicine](https://mlsanity.com/paper/2311.16452/) (2023)
- [Ex Machina: Personal Attacks Seen at Scale](https://mlsanity.com/paper/1610.08914/) (2016)
- [Build it Break it Fix it for Dialogue Safety: Robustness from Adversarial Human Attack](https://mlsanity.com/paper/1908.06083/) (2019)
- [ConstitutionMaker: Interactively Critiquing Large Language Models by Converting Feedback into Principles](https://mlsanity.com/paper/2310.15428/) (2023)
- [Towards Agile Text Classifiers for Everyone](https://mlsanity.com/paper/2302.06541/) (2023)

## Built on by (most cited first, 8 of 8)

- [Generating Robot Constitutions & Benchmarks for Semantic Safety](https://mlsanity.com/paper/2503.08663/) (2025)
- [Position: Towards Bidirectional Human-AI Alignment](https://mlsanity.com/paper/2406.09264/) (2024)
- [SPRI: Aligning Large Language Models with Context-Situated Principles](https://mlsanity.com/paper/2502.03397/) (2025)
- [Latent Principle Discovery for Language Model Self-Improvement](https://mlsanity.com/paper/2505.16927/) (2025)
- [POEM: Interactive Prompt Optimization for Enhancing Multimodal Reasoning of Large Language Models](https://mlsanity.com/paper/2406.03843/) (2024)
- [Gensors: Authoring Personalized Visual Sensors with Multimodal Foundation Models and Reasoning](https://mlsanity.com/paper/2501.15727/) (2025)
- [LM-Lexicon: Improving Definition Modeling via Harmonizing Semantic Experts](https://mlsanity.com/paper/2602.14060/) (2026)
- [AtomSearch: Evidence-Grounded Tree Search for Agent Skill Optimization](https://mlsanity.com/paper/2610.19951/) (2026)

## Abstract (arXiv)

Large language models (LLMs) are highly capable at a variety of tasks given the right prompt, but writing one is still a difficult and tedious process. In this work, we introduce ConstitutionalExperts, a method for learning a prompt consisting of constitutional principles (i.e. rules), given a training dataset. Unlike prior methods that optimize the prompt as a single entity, our method incrementally improves the prompt by surgically editing individual principles. We also show that we can improve overall performance by learning unique prompts for different semantic regions of the training data and using a mixture-of-experts (MoE) architecture to route inputs at inference time. We compare our method to other state of the art prompt-optimization techniques across six benchmark datasets. We also investigate whether MoE improves these other techniques. Our results suggest that ConstitutionalExperts outperforms other prompt optimization techniques by 10.9% (F1) and that mixture-of-experts improves all techniques, suggesting its broad applicability.