# Three Models of RLHF Annotation: Extension, Evidence, and Authority

arXiv: https://arxiv.org/abs/2604.25895 · HTML: https://mlsanity.com/paper/2604.25895/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Reward modeling and RLHF, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 28 of its 56 references that are in the map.
- First posted on arXiv 28 Apr 2026.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Reward modeling and RLHF](https://mlsanity.com/alignment/reward-modeling-and-rlhf/)

## Builds on (most cited first, 28 of 28)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [A General Language Assistant as a Laboratory for Alignment](https://mlsanity.com/paper/2112.00861/) (2021)
- [A General Theoretical Paradigm to Understand Learning from Human Preferences](https://mlsanity.com/paper/2310.12036/) (2023)
- [Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2307.15217/) (2023)
- [RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback](https://mlsanity.com/paper/2309.00267/) (2023)
- [Improving alignment of dialogue agents via targeted human judgements](https://mlsanity.com/paper/2209.14375/) (2022)
- [Artificial Intelligence, Values and Alignment](https://mlsanity.com/paper/2001.09768/) (2020)
- [A Roadmap to Pluralistic Alignment](https://mlsanity.com/paper/2402.05070/) (2024)
- [The PRISM Alignment Dataset: What Participatory, Representative and Individualised Human Feedback Reveals About the Subjective and Multicultural Alignment of Large Language Models](https://mlsanity.com/paper/2404.16019/) (2024)
- [HelpSteer: Multi-attribute Helpfulness Dataset for SteerLM](https://mlsanity.com/paper/2311.09528/) (2023)
- [MaxMin-RLHF: Alignment with Diverse Human Preferences](https://mlsanity.com/paper/2402.08925/) (2024)
- [Collective Constitutional AI: Aligning a Language Model with Public Input](https://mlsanity.com/paper/2406.07814/) (2024)
- [Jury Learning: Integrating Dissenting Voices into Machine Learning Models](https://mlsanity.com/paper/2202.02950/) (2022)
- [Unpacking DPO and PPO: Disentangling Best Practices for Learning from Preference Feedback](https://mlsanity.com/paper/2406.09279/) (2024)
- [Group Robust Preference Optimization in Reward-free RLHF](https://mlsanity.com/paper/2405.20304/) (2024)
- [PERSONA: A Reproducible Testbed for Pluralistic Alignment](https://mlsanity.com/paper/2407.17387/) (2024)
- [Inverse Constitutional AI: Compressing Preferences into Principles](https://mlsanity.com/paper/2406.06560/) (2024)
- [Democratising AI: Multiple Meanings, Goals, and Methods](https://mlsanity.com/paper/2303.12642/) (2023)
- [A Philosophical Introduction to Language Models -- Part I: Continuity With Classic Debates](https://mlsanity.com/paper/2401.03910/) (2024)
- [AI Alignment at Your Discretion](https://mlsanity.com/paper/2502.10441/) (2025)
- [How many labelers do you have? A closer look at gold-standard labels](https://mlsanity.com/paper/2206.12041/) (2022)
- [Legitimate Power, Illegitimate Automation: The problem of ignoring legitimacy in automated decision systems](https://mlsanity.com/paper/2404.15680/) (2024)

## Abstract (arXiv)

Preference-based alignment methods, most prominently Reinforcement Learning with Human Feedback (RLHF), use the judgments of human annotators to shape large language model behaviour. However, the normative role of these judgments is rarely made explicit. I distinguish three conceptual models of that role. The first is extension: annotators extend the system designers' own judgments about what outputs should be. The second is evidence: annotators provide independent evidence about some facts, whether moral, social or otherwise. The third is authority: annotators have some independent authority (as representatives of the broader population) to determine system outputs. I argue that these models have implications for how RLHF pipelines should solicit, validate and aggregate annotations. I survey landmark papers in the literature on RLHF and related methods to illustrate how they implicitly draw on these models, describe failure modes that come from unintentionally or intentionally conflating them, and offer normative criteria for choosing among them. My central recommendation is that RLHF pipeline designers should decompose annotation into separable dimensions and tailor each pipeline to the model most appropriate for that dimension, rather than seeking a single unified pipeline.