# From Values to Opinions: Predicting Human Behaviors and Stances Using Value-Injected Large Language Models

arXiv: https://arxiv.org/abs/2310.17857 · HTML: https://mlsanity.com/paper/2310.17857/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 31 references that are in the map.
- First posted on arXiv 27 Oct 2023.

## Builds on (most cited first, 12 of 12)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Cross-Task Generalization via Natural Language Crowdsourcing Instructions](https://mlsanity.com/paper/2104.08773/) (2021)
- [Large Language Models Can Self-Improve](https://mlsanity.com/paper/2210.11610/) (2022)
- [Learning To Retrieve Prompts for In-Context Learning](https://mlsanity.com/paper/2112.08633/) (2021)
- [Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studies](https://mlsanity.com/paper/2208.10264/) (2022)
- [Social Chemistry 101: Learning to Reason about Social and Moral Norms](https://mlsanity.com/paper/2011.00620/) (2020)
- [Probing Pre-Trained Language Models for Cross-Cultural Differences in Values](https://mlsanity.com/paper/2203.13722/) (2022)
- [Who is GPT-3? An Exploration of Personality, Values and Demographics](https://mlsanity.com/paper/2209.14338/) (2022)
- [Can ChatGPT Assess Human Personalities? A General Evaluation Framework](https://mlsanity.com/paper/2303.01248/) (2023)
- [Identifying and Manipulating the Personality Traits of Language Models](https://mlsanity.com/paper/2212.10276/) (2022)
- [The Touch'e23-ValueEval Dataset for Identifying Human Values behind Arguments](https://mlsanity.com/paper/2301.13771/) (2023)

## Built on by (most cited first, 10 of 10)

- [CLAVE: An Adaptive Framework for Evaluating Values of LLM Generated Responses](https://mlsanity.com/paper/2407.10725/) (2024)
- [Position: Towards Bidirectional Human-AI Alignment](https://mlsanity.com/paper/2406.09264/) (2024)
- [Do LLMs have Consistent Values?](https://mlsanity.com/paper/2407.12878/) (2024)
- [Harnessing LLMs for Cross-City OD Flow Prediction](https://mlsanity.com/paper/2409.03937/) (2024)
- [Knowing But Not Doing: Convergent Morality and Divergent Action in LLMs](https://mlsanity.com/paper/2601.07972/) (2026)
- [Counterfactual Reasoning for Steerable Pluralistic Value Alignment of Large Language Models](https://mlsanity.com/paper/2510.18526/) (2025)
- [AdAEM: An Adaptively and Automated Extensible Measurement of LLMs' Value Difference](https://mlsanity.com/paper/2505.13531/) (2025)
- [Multimodal Fusion with LLMs for Engagement Prediction in Natural Conversation](https://mlsanity.com/paper/2409.09135/) (2024)
- [Position: Align AI to Our Aspirations, Not Our Flaws](https://mlsanity.com/paper/2606.13755/) (2026)
- [What Do People Actually Want From AI? Mapping Preference Plurality](https://mlsanity.com/paper/2606.06674/) (2026)

## Abstract (arXiv)

Being able to predict people's opinions on issues and behaviors in realistic scenarios can be helpful in various domains, such as politics and marketing. However, conducting large-scale surveys like the European Social Survey to solicit people's opinions on individual issues can incur prohibitive costs. Leveraging prior research showing influence of core human values on individual decisions and actions, we propose to use value-injected large language models (LLM) to predict opinions and behaviors. To this end, we present Value Injection Method (VIM), a collection of two methods -- argument generation and question answering -- designed to inject targeted value distributions into LLMs via fine-tuning. We then conduct a series of experiments on four tasks to test the effectiveness of VIM and the possibility of using value-injected LLMs to predict opinions and behaviors of people. We find that LLMs value-injected with variations of VIM substantially outperform the baselines. Also, the results suggest that opinions and behaviors can be better predicted using value-injected LLMs than the baseline approaches.