# The PRISM Alignment Dataset: What Participatory, Representative and Individualised Human Feedback Reveals About the Subjective and Multicultural Alignment of Large Language Models

arXiv: https://arxiv.org/abs/2404.16019 · HTML: https://mlsanity.com/paper/2404.16019/

## Key facts

- Cited by 144 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 62 of its 163 references that are in the map.
- First posted on arXiv 24 Apr 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 62)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [Mixtral of Experts](https://mlsanity.com/paper/2401.04088/) (2024)
- [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)
- [LIMA: Less Is More for Alignment](https://mlsanity.com/paper/2305.11206/) (2023)
- [Model Cards for Model Reporting](https://mlsanity.com/paper/1810.03993/) (2018)
- [A General Language Assistant as a Laboratory for Alignment](https://mlsanity.com/paper/2112.00861/) (2021)
- [Gemini: A Family of Highly Capable Multimodal Models](https://mlsanity.com/paper/2312.11805/) (2023)
- [Whose Opinions Do Language Models Reflect?](https://mlsanity.com/paper/2303.17548/) (2023)
- [Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2307.15217/) (2023)
- [AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback](https://mlsanity.com/paper/2305.14387/) (2023)
- [Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned](https://mlsanity.com/paper/2209.07858/) (2022)
- [OpenAssistant Conversations -- Democratizing Large Language Model Alignment](https://mlsanity.com/paper/2304.07327/) (2023)
- [Improving alignment of dialogue agents via targeted human judgements](https://mlsanity.com/paper/2209.14375/) (2022)
- [RewardBench: Evaluating Reward Models for Language Modeling](https://mlsanity.com/paper/2403.13787/) (2024)
- [LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation Dataset](https://mlsanity.com/paper/2309.11998/) (2023)
- [Towards Measuring the Representation of Subjective Global Opinions in Language Models](https://mlsanity.com/paper/2306.16388/) (2023)
- [Fine-Grained Human Feedback Gives Better Rewards for Language Model Training](https://mlsanity.com/paper/2306.01693/) (2023)
- [Multimodal datasets: misogyny, pornography, and malignant stereotypes](https://mlsanity.com/paper/2110.01963/) (2021)
- [Teaching language models to support answers with verified quotes](https://mlsanity.com/paper/2203.11147/) (2022)
- [A Long Way to Go: Investigating Length Correlations in RLHF](https://mlsanity.com/paper/2310.03716/) (2023)
- [Way Off-Policy Batch Deep Reinforcement Learning of Implicit Human Preferences in Dialog](https://mlsanity.com/paper/1907.00456/) (2019)
- [Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Merging](https://mlsanity.com/paper/2310.11564/) (2023)

## Built on by (most cited first, 30 of 144)

- [Large Language Models Often Know When They Are Being Evaluated](https://mlsanity.com/paper/2505.23836/) (2025)
- [Measuring what Matters: Construct Validity in Large Language Model Benchmarks](https://mlsanity.com/paper/2511.04703/) (2025)
- [Modular Pluralism: Pluralistic Alignment via Multi-LLM Collaboration](https://mlsanity.com/paper/2406.15951/) (2024)
- [Can LLM be a Personalized Judge?](https://mlsanity.com/paper/2406.11657/) (2024)
- [The Multilingual Alignment Prism: Aligning Global and Local Preferences to Reduce Harm](https://mlsanity.com/paper/2406.18682/) (2024)
- [Benchmarking Distributional Alignment of Large Language Models](https://mlsanity.com/paper/2411.05403/) (2024)
- [Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2504.12501/) (2025)
- [Flipping the Dialogue: Training and Evaluating User Language Models](https://mlsanity.com/paper/2510.06552/) (2025)
- [Values in the Wild: Discovering and Analyzing Values in Real-World Language Model Interactions](https://mlsanity.com/paper/2504.15236/) (2025)
- [Preference Learning Algorithms Do Not Learn Preference Rankings](https://mlsanity.com/paper/2405.19534/) (2024)
- [The State of Multilingual LLM Safety Research: From Measuring the Language Gap to Mitigating It](https://mlsanity.com/paper/2505.24119/) (2025)
- [HumanLM: Simulating Users with State Alignment Beats Response Imitation](https://mlsanity.com/paper/2603.03303/) (2026)
- [Can Language Models Reason about Individualistic Human Values and Preferences?](https://mlsanity.com/paper/2410.03868/) (2024)
- [Culturally Aware and Adapted NLP: A Taxonomy and a Survey of the State of the Art](https://mlsanity.com/paper/2406.03930/) (2024)
- [IssueBench: Millions of Realistic Prompts for Measuring Issue Bias in LLM Writing Assistance](https://mlsanity.com/paper/2502.08395/) (2025)
- [On Benchmarking Human-Like Intelligence in Machines](https://mlsanity.com/paper/2502.20502/) (2025)
- [Extrinsic Evaluation of Cultural Competence in Large Language Models](https://mlsanity.com/paper/2406.11565/) (2024)
- [CUPID: Evaluating Personalized and Contextualized Alignment of LLMs from Interactions](https://mlsanity.com/paper/2508.01674/) (2025)
- [Towards Data-Centric RLHF: Simple Metrics for Preference Dataset Comparison](https://mlsanity.com/paper/2409.09603/) (2024)
- [AI Alignment at Your Discretion](https://mlsanity.com/paper/2502.10441/) (2025)
- [Multilingual Large Language Models: A Systematic Survey](https://mlsanity.com/paper/2411.11072/) (2024)
- [Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas](https://mlsanity.com/paper/2505.14633/) (2025)
- [PRIME: Large Language Model Personalization with Cognitive Dual-Memory and Personalized Thought Process](https://mlsanity.com/paper/2507.04607/) (2025)
- [Cultural Palette: Pluralising Culture Alignment via Multi-agent Palette](https://mlsanity.com/paper/2412.11167/) (2024)
- [FSPO: Few-Shot Optimization of Synthetic Preferences Personalizes to Real Users](https://mlsanity.com/paper/2502.19312/) (2025)
- [The AI Gap: How Socioeconomic Status Affects Language Technology Interactions](https://mlsanity.com/paper/2505.12158/) (2025)
- [Alignment and Safety in Large Language Models: Safety Mechanisms, Training Paradigms, and Emerging Challenges](https://mlsanity.com/paper/2507.19672/) (2025)
- [Pairwise Calibrated Rewards for Pluralistic Alignment](https://mlsanity.com/paper/2506.06298/) (2025)
- [MMPB: It's Time for Multi-Modal Personalization](https://mlsanity.com/paper/2509.22820/) (2025)
- [Hire Your Anthropologist! Rethinking Culture Benchmarks Through an Anthropological Lens](https://mlsanity.com/paper/2510.05931/) (2025)

## Abstract (arXiv)

Human feedback is central to the alignment of Large Language Models (LLMs). However, open questions remain about methods (how), domains (where), people (who) and objectives (to what end) of feedback processes. To navigate these questions, we introduce PRISM, a dataset that maps the sociodemographics and stated preferences of 1,500 diverse participants from 75 countries, to their contextual preferences and fine-grained feedback in 8,011 live conversations with 21 LLMs. With PRISM, we contribute (i) wider geographic and demographic participation in feedback; (ii) census-representative samples for two countries (UK, US); and (iii) individualised ratings that link to detailed participant profiles, permitting personalisation and attribution of sample artefacts. We target subjective and multicultural perspectives on value-laden and controversial issues, where we expect interpersonal and cross-cultural disagreement. We use PRISM in three case studies to demonstrate the need for careful consideration of which humans provide what alignment data.