# Aligning Language Models to User Opinions

arXiv: https://arxiv.org/abs/2305.14929 · HTML: https://mlsanity.com/paper/2305.14929/

## Key facts

- Cited by 99 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 11 of its 32 references that are in the map.
- First posted on arXiv 24 May 2023.

## 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, 11 of 11)

- [Neural Collaborative Filtering](https://mlsanity.com/paper/1708.05031/) (2017)
- [Generalization through Memorization: Nearest Neighbor Language Models](https://mlsanity.com/paper/1911.00172/) (2019)
- [Whose Opinions Do Language Models Reflect?](https://mlsanity.com/paper/2303.17548/) (2023)
- [LaMP: When Large Language Models Meet Personalization](https://mlsanity.com/paper/2304.11406/) (2023)
- [Toxicity in ChatGPT: Analyzing Persona-assigned Language Models](https://mlsanity.com/paper/2304.05335/) (2023)
- [Chat-REC: Towards Interactive and Explainable LLMs-Augmented Recommender System](https://mlsanity.com/paper/2303.14524/) (2023)
- [Generating Personalized Recipes from Historical User Preferences](https://mlsanity.com/paper/1909.00105/) (2019)
- [Language Models Trained on Media Diets Can Predict Public Opinion](https://mlsanity.com/paper/2303.16779/) (2023)
- [Echo Chambers: Emotional Contagion and Group Polarization on Facebook](https://mlsanity.com/paper/1607.01032/) (2016)
- [Improving Question Answering with External Knowledge](https://mlsanity.com/paper/1902.00993/) (2019)
- [Self-Supervised Bot Play for Conversational Recommendation with Justifications](https://mlsanity.com/paper/2112.05197/) (2021)

## Built on by (most cited first, 30 of 99)

- [A Roadmap to Pluralistic Alignment](https://mlsanity.com/paper/2402.05070/) (2024)
- [Towards Measuring and Modeling "Culture" in LLMs: A Survey](https://mlsanity.com/paper/2403.15412/) (2024)
- [A Comprehensive Study of Knowledge Editing for Large Language Models](https://mlsanity.com/paper/2401.01286/) (2024)
- [Simulating Opinion Dynamics with Networks of LLM-based Agents](https://mlsanity.com/paper/2311.09618/) (2023)
- [Personalized Language Modeling from Personalized Human Feedback](https://mlsanity.com/paper/2402.05133/) (2024)
- [Sensitivity, Performance, Robustness: Deconstructing the Effect of Sociodemographic Prompting](https://mlsanity.com/paper/2309.07034/) (2023)
- [Evaluating Large Language Model Biases in Persona-Steered Generation](https://mlsanity.com/paper/2405.20253/) (2024)
- [PERSONA: A Reproducible Testbed for Pluralistic Alignment](https://mlsanity.com/paper/2407.17387/) (2024)
- [Language Model Fine-Tuning on Scaled Survey Data for Predicting Distributions of Public Opinions](https://mlsanity.com/paper/2502.16761/) (2025)
- [Group Preference Optimization: Few-Shot Alignment of Large Language Models](https://mlsanity.com/paper/2310.11523/) (2023)
- [PersonalLLM: Tailoring LLMs to Individual Preferences](https://mlsanity.com/paper/2409.20296/) (2024)
- [PAD: Personalized Alignment of LLMs at Decoding-Time](https://mlsanity.com/paper/2410.04070/) (2024)
- [On the steerability of large language models toward data-driven personas](https://mlsanity.com/paper/2311.04978/) (2023)
- [Virtual Personas for Language Models via an Anthology of Backstories](https://mlsanity.com/paper/2407.06576/) (2024)
- [Persona-DB: Efficient Large Language Model Personalization for Response Prediction with Collaborative Data Refinement](https://mlsanity.com/paper/2402.11060/) (2024)
- [Random Silicon Sampling: Simulating Human Sub-Population Opinion Using a Large Language Model Based on Group-Level Demographic Information](https://mlsanity.com/paper/2402.18144/) (2024)
- [RLHF Can Speak Many Languages: Unlocking Multilingual Preference Optimization for LLMs](https://mlsanity.com/paper/2407.02552/) (2024)
- [The Prompt Makes the Person(a): A Systematic Evaluation of Sociodemographic Persona Prompting for Large Language Models](https://mlsanity.com/paper/2507.16076/) (2025)
- [Evaluating Cultural Adaptability of a Large Language Model via Simulation of Synthetic Personas](https://mlsanity.com/paper/2408.06929/) (2024)
- [HumanLM: Simulating Users with State Alignment Beats Response Imitation](https://mlsanity.com/paper/2603.03303/) (2026)
- [Sociodemographic Prompting is Not Yet an Effective Approach for Simulating Subjective Judgments with LLMs](https://mlsanity.com/paper/2311.09730/) (2023)
- [CoQuest: Exploring Research Question Co-Creation with an LLM-based Agent](https://mlsanity.com/paper/2310.06155/) (2023)
- [ChatBench: From Static Benchmarks to Human-AI Evaluation](https://mlsanity.com/paper/2504.07114/) (2025)
- [Few-shot Personalization of LLMs with Mis-aligned Responses](https://mlsanity.com/paper/2406.18678/) (2024)
- [Value Profiles for Encoding Human Variation](https://mlsanity.com/paper/2503.15484/) (2025)
- [SynthesizeMe! Inducing Persona-Guided Prompts for Personalized Reward Models in LLMs](https://mlsanity.com/paper/2506.05598/) (2025)
- [Culturally Aware and Adapted NLP: A Taxonomy and a Survey of the State of the Art](https://mlsanity.com/paper/2406.03930/) (2024)
- [Cultural Conditioning or Placebo? On the Effectiveness of Socio-Demographic Prompting](https://mlsanity.com/paper/2406.11661/) (2024)
- [The Potential and Challenges of Evaluating Attitudes, Opinions, and Values in Large Language Models](https://mlsanity.com/paper/2406.11096/) (2024)
- [Self-Alignment: Improving Alignment of Cultural Values in LLMs via In-Context Learning](https://mlsanity.com/paper/2408.16482/) (2024)

## Abstract (arXiv)

An important aspect of developing LLMs that interact with humans is to align models' behavior to their users. It is possible to prompt an LLM into behaving as a certain persona, especially a user group or ideological persona the model captured during its pertaining stage. But, how to best align an LLM with a specific user and not a demographic or ideological group remains an open question. Mining public opinion surveys (by Pew Research), we find that the opinions of a user and their demographics and ideologies are not mutual predictors. We use this insight to align LLMs by modeling both user opinions as well as user demographics and ideology, achieving up to 7 points accuracy gains in predicting public opinions from survey questions across a broad set of topics. In addition to the typical approach of prompting LLMs with demographics and ideology, we discover that utilizing the most relevant past opinions from individual users enables the model to predict user opinions more accurately.