# Scopes of Alignment

arXiv: https://arxiv.org/abs/2501.12405 · HTML: https://mlsanity.com/paper/2501.12405/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Human values and AI feedback alignment, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 14 of its 31 references that are in the map.
- First posted on arXiv 15 Jan 2025.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Human values and AI feedback alignment](https://mlsanity.com/alignment/human-values-and-ai-feedback-alignment/)

## Builds on (most cited first, 14 of 14)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!](https://mlsanity.com/paper/2310.03693/) (2023)
- [Towards Measuring the Representation of Subjective Global Opinions in Language Models](https://mlsanity.com/paper/2306.16388/) (2023)
- [From Pretraining Data to Language Models to Downstream Tasks: Tracking the Trails of Political Biases Leading to Unfair NLP Models](https://mlsanity.com/paper/2305.08283/) (2023)
- [Large Language Model Alignment: A Survey](https://mlsanity.com/paper/2309.15025/) (2023)
- [Evaluating the Moral Beliefs Encoded in LLMs](https://mlsanity.com/paper/2307.14324/) (2023)
- [Larimar: Large Language Models with Episodic Memory Control](https://mlsanity.com/paper/2403.11901/) (2024)
- [LAB: Large-Scale Alignment for ChatBots](https://mlsanity.com/paper/2403.01081/) (2024)
- [Speaking Multiple Languages Affects the Moral Bias of Language Models](https://mlsanity.com/paper/2211.07733/) (2022)
- [Mutual Theory of Mind for Human-AI Communication](https://mlsanity.com/paper/2210.03842/) (2022)
- [Banishing LLM Hallucinations Requires Rethinking Generalization](https://mlsanity.com/paper/2406.17642/) (2024)
- [Alignment Studio: Aligning Large Language Models to Particular Contextual Regulations](https://mlsanity.com/paper/2403.09704/) (2024)
- [HCC Is All You Need: Alignment-The Sensible Kind Anyway-Is Just Human-Centered Computing](https://mlsanity.com/paper/2405.03699/) (2024)

## Built on by (most cited first, 3 of 3)

- [The Effectiveness of Approximate Regularized Replay for Efficient Supervised Fine-Tuning of Large Language Models](https://mlsanity.com/paper/2512.22337/) (2025)
- [Position: Collusion Risks Among AI Reasoning Agents Justify Certification Requirements for Making Market Decisions](https://mlsanity.com/paper/2608.18078/) (2026)
- [From Normative Frameworks to Alignment Data: Constructing and Evaluating SFT and Preference Data](https://mlsanity.com/paper/2609.35201/) (2026)

## Abstract (arXiv)

Much of the research focus on AI alignment seeks to align large language models and other foundation models to the context-less and generic values of helpfulness, harmlessness, and honesty. Frontier model providers also strive to align their models with these values. In this paper, we motivate why we need to move beyond such a limited conception and propose three dimensions for doing so. The first scope of alignment is competence: knowledge, skills, or behaviors the model must possess to be useful for its intended purpose. The second scope of alignment is transience: either semantic or episodic depending on the context of use. The third scope of alignment is audience: either mass, public, small-group, or dyadic. At the end of the paper, we use the proposed framework to position some technologies and workflows that go beyond prevailing notions of alignment.