mlsanityData to 7 Oct 2026

Scopes of Alignment

arXiv 2501.12405 ↗First posted 15 Jan 2025cs.CY cs.AI cs.CLcited by 3

On the map: LLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment

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.

Key facts. Cited by 3 papers in the map (data through 7 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.

Builds on

14 of 31 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024Alignment Studio: Aligning Large Language Models to Particular Contextual Regulations8 Mar
  2. 2022Constitutional AI: Harmlessness from AI Feedback15 Dec

Other references · 12

  1. 2022Training language models to follow instructions with human feedbackcited by 15,712
  2. 2023Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!cited by 1,106
  3. 2023Towards Measuring the Representation of Subjective Global Opinions in Language Modelscited by 424
  4. 2023From Pretraining Data to Language Models to Downstream Tasks: Tracking the Trails of Political Biases Leading to Unfair NLP Modelscited by 257
  5. 2023Large Language Model Alignment: A Surveycited by 241
  6. 2023Evaluating the Moral Beliefs Encoded in LLMscited by 211
  7. 2024Larimar: Large Language Models with Episodic Memory Controlcited by 53
  8. 2024LAB: Large-Scale Alignment for ChatBotscited by 39
  9. 2022Speaking Multiple Languages Affects the Moral Bias of Language Modelscited by 34
  10. 2022Mutual Theory of Mind for Human-AI Communicationcited by 15
  11. 2024Banishing LLM Hallucinations Requires Rethinking Generalizationcited by 13
  12. 2024HCC Is All You Need: Alignment-The Sensible Kind Anyway-Is Just Human-Centered Computingcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 2.

3 papers.

  1. 2025The Effectiveness of Approximate Regularized Replay for Efficient Supervised Fine-Tuning of Large Language Modelscited by 2
  2. 2026Position: Collusion Risks Among AI Reasoning Agents Justify Certification Requirements for Making Market Decisionscited by 1
  3. 2026From Normative Frameworks to Alignment Data: Constructing and Evaluating SFT and Preference Datacited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Decoding Alignment: A Critical Survey of LLM Development Initiatives through Value-setting and Data-centric Lens
  2. 2025'Too much alignment; not enough culture': Re-balancing cultural alignment practices in LLMs
  3. 2024Position: Towards Bidirectional Human-AI Alignment
  4. 2024On the Essence and Prospect: An Investigation of Alignment Approaches for Big Models
  5. 2023From Instructions to Intrinsic Human Values -- A Survey of Alignment Goals for Big Models
  6. 2025Dynamic Alignment for Collective Agency: Toward a Scalable Self-Improving Framework for Open-Ended LLM Alignment
  7. 2024The AI Alignment Paradox
  8. 2025CALMA: A Process for Deriving Context-aligned Axes for Language Model Alignment