# Beyond the Binary: Capturing Diverse Preferences With Reward Regularization

arXiv: https://arxiv.org/abs/2412.03822 · HTML: https://mlsanity.com/paper/2412.03822/

## Key facts

- Cited by 11 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 36 of its 49 references that are in the map.
- First posted on arXiv 5 Dec 2024.

## 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, 30 of 36)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (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)
- [WebGPT: Browser-assisted question-answering with human feedback](https://mlsanity.com/paper/2112.09332/) (2021)
- [LaMDA: Language Models for Dialog Applications](https://mlsanity.com/paper/2201.08239/) (2022)
- [SimPO: Simple Preference Optimization with a Reference-Free Reward](https://mlsanity.com/paper/2405.14734/) (2024)
- [Whose Opinions Do Language Models Reflect?](https://mlsanity.com/paper/2303.17548/) (2023)
- [Out of One, Many: Using Language Models to Simulate Human Samples](https://mlsanity.com/paper/2209.06899/) (2022)
- [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)
- [Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Merging](https://mlsanity.com/paper/2310.11564/) (2023)
- [Pretraining Language Models with Human Preferences](https://mlsanity.com/paper/2302.08582/) (2023)
- [Rewarded soups: towards Pareto-optimal alignment by interpolating weights fine-tuned on diverse rewards](https://mlsanity.com/paper/2306.04488/) (2023)
- [Fine-tuning language models to find agreement among humans with diverse preferences](https://mlsanity.com/paper/2211.15006/) (2022)
- [A Roadmap to Pluralistic Alignment](https://mlsanity.com/paper/2402.05070/) (2024)
- [Personalizing Reinforcement Learning from Human Feedback with Variational Preference Learning](https://mlsanity.com/paper/2408.10075/) (2024)
- [Distributional Preference Learning: Understanding and Accounting for Hidden Context in RLHF](https://mlsanity.com/paper/2312.08358/) (2023)
- [Personalized Language Modeling from Personalized Human Feedback](https://mlsanity.com/paper/2402.05133/) (2024)
- [Collective Constitutional AI: Aligning a Language Model with Public Input](https://mlsanity.com/paper/2406.07814/) (2024)
- [DICES Dataset: Diversity in Conversational AI Evaluation for Safety](https://mlsanity.com/paper/2306.11247/) (2023)
- [MMToM-QA: Multimodal Theory of Mind Question Answering](https://mlsanity.com/paper/2401.08743/) (2024)
- [Uncertainty-aware Reward Model: Teaching Reward Models to Know What is Unknown](https://mlsanity.com/paper/2410.00847/) (2024)
- [The Past, Present and Better Future of Feedback Learning in Large Language Models for Subjective Human Preferences and Values](https://mlsanity.com/paper/2310.07629/) (2023)
- [Whose Language Counts as High Quality? Measuring Language Ideologies in Text Data Selection](https://mlsanity.com/paper/2201.10474/) (2022)
- [Beyond Preferences in AI Alignment](https://mlsanity.com/paper/2408.16984/) (2024)

## Built on by (most cited first, 11 of 11)

- [Diverse Preference Optimization](https://mlsanity.com/paper/2501.18101/) (2025)
- [Improving LLM-as-a-Judge Inference with the Judgment Distribution](https://mlsanity.com/paper/2503.03064/) (2025)
- [Whose Boat Does it Float? Improving Personalization in Preference Tuning via Inferred User Personas](https://mlsanity.com/paper/2501.11549/) (2025)
- [Robust LLM Alignment via Distributionally Robust Direct Preference Optimization](https://mlsanity.com/paper/2502.01930/) (2025)
- [When Personalization Meets Reality: A Multi-Faceted Analysis of Personalized Preference Learning](https://mlsanity.com/paper/2502.19158/) (2025)
- [Towards Reward Fairness in RLHF: From a Resource Allocation Perspective](https://mlsanity.com/paper/2505.23349/) (2025)
- [Online Distributionally Robust LLM Alignment via Regression to Relative Reward](https://mlsanity.com/paper/2509.19104/) (2025)
- [DeDPO: Debiased Direct Preference Optimization for Diffusion Models](https://mlsanity.com/paper/2602.06195/) (2026)
- [Learning to vary: Teaching LMs to reproduce human linguistic variability in next-word prediction](https://mlsanity.com/paper/2509.17794/) (2025)
- [Trust, Don't Trust, or Flip: Robust Preference-Based Reinforcement Learning with Multi-Expert Feedback](https://mlsanity.com/paper/2601.18751/) (2026)
- [What Do People Actually Want From AI? Mapping Preference Plurality](https://mlsanity.com/paper/2606.06674/) (2026)

## Abstract (arXiv)

Large language models (LLMs) are increasingly deployed via public-facing interfaces to interact with millions of users, each with diverse preferences. Despite this, preference tuning of LLMs predominantly relies on reward models trained using binary judgments where annotators select the preferred choice out of pairs of model outputs. In this work, we argue that this reliance on binary choices does not capture the broader, aggregate preferences of the target user in real-world tasks. We propose a taxonomy that identifies two dimensions of subjectivity where different users disagree on the preferred output-namely, the Plurality of Responses to Prompts, where prompts allow for multiple correct answers, and the Indistinguishability of Responses, where candidate outputs are paraphrases of each other. We show that reward models correlate weakly with user preferences in these cases. As a first step to address this issue, we introduce a simple yet effective method that augments existing binary preference datasets with synthetic preference judgments to estimate potential user disagreement. Incorporating these via a margin term as a form of regularization during model training yields predictions that better align with the aggregate user preferences.