# Embedding Democratic Values into Social Media AIs via Societal Objective Functions

arXiv: https://arxiv.org/abs/2307.13912 · HTML: https://mlsanity.com/paper/2307.13912/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 116 references that are in the map.
- First posted on arXiv 26 Jul 2023.

## Builds on (most cited first, 27 of 27)

- [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)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [StereoSet: Measuring stereotypical bias in pretrained language models](https://mlsanity.com/paper/2004.09456/) (2020)
- [Ignore Previous Prompt: Attack Techniques For Language Models](https://mlsanity.com/paper/2211.09527/) (2022)
- [Whose Opinions Do Language Models Reflect?](https://mlsanity.com/paper/2303.17548/) (2023)
- [Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes](https://mlsanity.com/paper/2305.02301/) (2023)
- [The Woman Worked as a Babysitter: On Biases in Language Generation](https://mlsanity.com/paper/1909.01326/) (2019)
- [Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks](https://mlsanity.com/paper/2302.05733/) (2023)
- [Can Large Language Models Transform Computational Social Science?](https://mlsanity.com/paper/2305.03514/) (2023)
- [Want To Reduce Labeling Cost? GPT-3 Can Help](https://mlsanity.com/paper/2108.13487/) (2021)
- [Is ChatGPT better than Human Annotators? Potential and Limitations of ChatGPT in Explaining Implicit Hate Speech](https://mlsanity.com/paper/2302.07736/) (2023)
- [Distilling Task-Specific Knowledge from BERT into Simple Neural Networks](https://mlsanity.com/paper/1903.12136/) (2019)
- [Fairness in Machine Learning: Lessons from Political Philosophy](https://mlsanity.com/paper/1712.03586/) (2017)
- [Supporting Qualitative Analysis with Large Language Models: Combining Codebook with GPT-3 for Deductive Coding](https://mlsanity.com/paper/2304.10548/) (2023)
- [Automated Annotation with Generative AI Requires Validation](https://mlsanity.com/paper/2306.00176/) (2023)
- [Algorithmic Amplification of Politics on Twitter](https://mlsanity.com/paper/2110.11010/) (2021)
- [The Challenge of Understanding What Users Want: Inconsistent Preferences and Engagement Optimization](https://mlsanity.com/paper/2202.11776/) (2022)
- [Accuracy and Political Bias of News Source Credibility Ratings by Large Language Models](https://mlsanity.com/paper/2304.00228/) (2023)
- [Building Human Values into Recommender Systems: An Interdisciplinary Synthesis](https://mlsanity.com/paper/2207.10192/) (2022)
- [From Optimizing Engagement to Measuring Value](https://mlsanity.com/paper/2008.12623/) (2020)
- [How algorithmic popularity bias hinders or promotes quality](https://mlsanity.com/paper/1707.00574/) (2017)
- [Bridging Systems: Open Problems for Countering Destructive Divisiveness across Ranking, Recommenders, and Governance](https://mlsanity.com/paper/2301.09976/) (2023)
- [Understanding Effects of Algorithmic vs. Community Label on Perceived Accuracy of Hyper-partisan Misinformation](https://mlsanity.com/paper/2203.00710/) (2022)
- [Manipulating Twitter Through Deletions](https://mlsanity.com/paper/2203.13893/) (2022)
- [Perspective-taking to Reduce Affective Polarization on Social Media](https://mlsanity.com/paper/2110.05596/) (2021)

## Built on by (most cited first, 25 of 25)

- [Backdooring Instruction-Tuned Large Language Models with Virtual Prompt Injection](https://mlsanity.com/paper/2307.16888/) (2023)
- [Distributional Preference Learning: Understanding and Accounting for Hidden Context in RLHF](https://mlsanity.com/paper/2312.08358/) (2023)
- [Concept Induction: Analyzing Unstructured Text with High-Level Concepts Using LLooM](https://mlsanity.com/paper/2404.12259/) (2024)
- [DarkBench: Benchmarking Dark Patterns in Large Language Models](https://mlsanity.com/paper/2503.10728/) (2025)
- [How Susceptible are Large Language Models to Ideological Manipulation?](https://mlsanity.com/paper/2402.11725/) (2024)
- [Wikibench: Community-Driven Data Curation for AI Evaluation on Wikipedia](https://mlsanity.com/paper/2402.14147/) (2024)
- [Value Imprint: A Technique for Auditing the Human Values Embedded in RLHF Datasets](https://mlsanity.com/paper/2411.11937/) (2024)
- [Meaning Is Not A Metric: Using LLMs to make cultural context legible at scale](https://mlsanity.com/paper/2505.23785/) (2025)
- [What do Large Language Models Say About Animals? Investigating Risks of Animal Harm in Generated Text](https://mlsanity.com/paper/2503.04804/) (2025)
- [CoBRA: Programming Cognitive Bias in Social Agents Using Classic Social Science Experiments](https://mlsanity.com/paper/2509.13588/) (2025)
- [Legal Minds, Algorithmic Decisions: How LLMs Apply Constitutional Principles in Complex Scenarios](https://mlsanity.com/paper/2407.19760/) (2024)
- [Reranking partisan animosity in algorithmic social media feeds alters affective polarization](https://mlsanity.com/paper/2411.14652/) (2024)
- [Fine-tuned Large Language Models (LLMs): Improved Prompt Injection Attacks Detection](https://mlsanity.com/paper/2410.21337/) (2024)
- [Value Alignment of Social Media Ranking Algorithms](https://mlsanity.com/paper/2509.14434/) (2025)
- [CTRL-Rec: Controlling Recommender Systems With Natural Language](https://mlsanity.com/paper/2510.12742/) (2025)
- [Representative Ranking for Deliberation in the Public Sphere](https://mlsanity.com/paper/2503.18962/) (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)
- [Large Language Models, and LLM-Based Agents, Should Be Used to Enhance the Digital Public Sphere](https://mlsanity.com/paper/2410.12123/) (2024)
- [The Burden of Interactive Alignment with Inconsistent Preferences](https://mlsanity.com/paper/2510.16368/) (2025)
- [Cooperative Evolutionary Pressure and Diminishing Returns Might Explain the Fermi Paradox: On What Super-AIs Are Like](https://mlsanity.com/paper/2404.03685/) (2024)
- [Kaleidoscope Gallery: Exploring Ethics and Generative AI Through Art](https://mlsanity.com/paper/2505.14758/) (2025)
- [Recommender system in X inadvertently profiles ideological positions of users](https://mlsanity.com/paper/2602.02624/) (2026)
- [LLM-Assisted Reranking to Operationalize Nuanced Objectives in Recommender Systems](https://mlsanity.com/paper/2606.02883/) (2026)
- [Who Plays Which Role When? Communication Role Dynamics for Peer Recognition and Team Performance Prediction](https://mlsanity.com/paper/2606.28544/) (2026)
- [Compass: Continuously Aligning Social Media Feeds via In-Situ Reflections](https://mlsanity.com/paper/2608.04274/) (2026)

## Abstract (arXiv)

Can we design artificial intelligence (AI) systems that rank our social media feeds to consider democratic values such as mitigating partisan animosity as part of their objective functions? We introduce a method for translating established, vetted social scientific constructs into AI objective functions, which we term societal objective functions, and demonstrate the method with application to the political science construct of anti-democratic attitudes. Traditionally, we have lacked observable outcomes to use to train such models, however, the social sciences have developed survey instruments and qualitative codebooks for these constructs, and their precision facilitates translation into detailed prompts for large language models. We apply this method to create a democratic attitude model that estimates the extent to which a social media post promotes anti-democratic attitudes, and test this democratic attitude model across three studies. In Study 1, we first test the attitudinal and behavioral effectiveness of the intervention among US partisans (N=1,380) by manually annotating (alpha=.895) social media posts with anti-democratic attitude scores and testing several feed ranking conditions based on these scores. Removal (d=.20) and downranking feeds (d=.25) reduced participants' partisan animosity without compromising their experience and engagement. In Study 2, we scale up the manual labels by creating the democratic attitude model, finding strong agreement with manual labels (rho=.75). Finally, in Study 3, we replicate Study 1 using the democratic attitude model instead of manual labels to test its attitudinal and behavioral impact (N=558), and again find that the feed downranking using the societal objective function reduced partisan animosity (d=.25). This method presents a novel strategy to draw on social science theory and methods to mitigate societal harms in social media AIs.