# Aligning Large Language Models with Human Opinions through Persona Selection and Value--Belief--Norm Reasoning

arXiv: https://arxiv.org/abs/2311.08385 · HTML: https://mlsanity.com/paper/2311.08385/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 6 of its 53 references that are in the map.
- First posted on arXiv 14 Nov 2023.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)
- 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, 6 of 6)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [Improving alignment of dialogue agents via targeted human judgements](https://mlsanity.com/paper/2209.14375/) (2022)
- [Aligning Large Language Models with Human: A Survey](https://mlsanity.com/paper/2307.12966/) (2023)

## Built on by (most cited first, 19 of 19)

- [The Prompt Makes the Person(a): A Systematic Evaluation of Sociodemographic Persona Prompting for Large Language Models](https://mlsanity.com/paper/2507.16076/) (2025)
- [LLMs Are Biased Towards Output Formats! Systematically Evaluating and Mitigating Output Format Bias of LLMs](https://mlsanity.com/paper/2408.08656/) (2024)
- [Whose Personae? Synthetic Persona Experiments in LLM Research and Pathways to Transparency](https://mlsanity.com/paper/2512.00461/) (2025)
- [One Persona, Many Cues, Different Results: How Sociodemographic Cues Impact LLM Personalization](https://mlsanity.com/paper/2601.18572/) (2026)
- [Survey Response Generation: Generating Closed-Ended Survey Responses In-Silico with Large Language Models](https://mlsanity.com/paper/2510.11586/) (2025)
- [What Makes a Good Natural Language Prompt?](https://mlsanity.com/paper/2506.06950/) (2025)
- [EtiCor++: Towards Understanding Etiquettical Bias in LLMs](https://mlsanity.com/paper/2506.08488/) (2025)
- [Political Bias Audits of LLMs Capture Sycophancy to the Inferred Auditor](https://mlsanity.com/paper/2604.27633/) (2026)
- [Inertia in Moral and Value Judgments of Large Language Models](https://mlsanity.com/paper/2408.09049/) (2024)
- [Improving the Distributional Alignment of LLMs using Supervision](https://mlsanity.com/paper/2507.00439/) (2025)
- [AI and My Values: User Perceptions of LLMs' Ability to Extract, Embody, and Explain Human Values from Casual Conversations](https://mlsanity.com/paper/2601.22440/) (2026)
- [DynSess: Dynamic Session-Level Evaluation and Optimization Framework for Role-Playing Agents](https://mlsanity.com/paper/2605.29256/) (2026)
- [Structuring the Space of Sociotechnical Alignment](https://mlsanity.com/paper/2607.01250/) (2026)
- [PrimeX: A Dataset of Worldview, Opinion, and Explanation](https://mlsanity.com/paper/2510.00174/) (2025)
- [More Than 1v1: Human-AI Alignment in Early Developmental Communities with Multimodal LLMs](https://mlsanity.com/paper/2603.07134/) (2026)
- [Toward Human-Centered Multi-Agent Systems: Integrating Cognition, Culture, Values, and Cooperation in AI Agents](https://mlsanity.com/paper/2606.08274/) (2026)
- [Signal or Spurious Cue? A Randomized Audit of Survey-Country Metadata in LLM Social Inference](https://mlsanity.com/paper/2608.06085/) (2026)
- [Who Would You Vote For? Auditing Political Alignment in LLMs: An Italian Case-Study](https://mlsanity.com/paper/2608.11649/) (2026)
- [OmouAI: Argumentative Human-AI Policy Deliberation with Simulated Personas](https://mlsanity.com/paper/2609.31078/) (2026)

## Abstract (arXiv)

Reasoning and predicting human opinions with large language models (LLMs) is essential yet challenging. Current methods employ role-playing with personae but face two major issues: LLMs are sensitive to even a single irrelevant persona, skewing predictions by up to 30%, and LLMs fail to reason strategically over personae. We propose Chain-of-Opinion (COO), a simple four-step solution modeling which and how to reason with personae, inspired by the Value--Belief--Norm (VBN) theory. COO differentiates between explicit personae (demographics and ideology) and implicit personae (historical opinions), involves: (1) filtering irrelevant attributes from explicit personae, (2) ranking implicit personae into a preferential list for selecting top-k, (3) applying novel VBN reasoning to extract user environmental and personal value, belief, and norm variables for accurate and reliable predictions, and (4) iterating VBN reasoning with progressively larger lists of implicit personae to handle potential persona insufficiency. COO efficiently achieves new state-of-the-art opinion prediction via prompting with only 5 inference calls, improving prior techniques by up to 4%. Notably, fine-tuning LMs with COO data results in significantly better opinion-aligned models, by up to 23%.