# User-Driven Value Alignment: Understanding Users' Perceptions and Strategies for Addressing Biased and Discriminatory Statements in AI Companions

arXiv: https://arxiv.org/abs/2409.00862 · HTML: https://mlsanity.com/paper/2409.00862/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Sep 2024.

## Built on by (most cited first, 14 of 14)

- [POET: Supporting Prompting Creativity and Personalization with Automated Expansion of Text-to-Image Generation](https://mlsanity.com/paper/2504.13392/) (2025)
- [Beyond One-Way Influence: Bidirectional Opinion Dynamics in Multi-Turn Human-LLM Interactions](https://mlsanity.com/paper/2510.20039/) (2025)
- [Enhancing Value Alignment of LLMs with Multi-agent system and Combinatorial Fusion](https://mlsanity.com/paper/2603.11126/) (2026)
- [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)
- [How Do Users Negotiate Harmful Value Conflicts with AI Companions? A Study with Minion, a Technology Probe for In-Situ Human-AI Conflict Response](https://mlsanity.com/paper/2411.07042/) (2024)
- [AI LEGO: Scaffolding Cross-Functional Collaboration in Industrial Responsible AI Practices during Early Design Stages](https://mlsanity.com/paper/2505.10300/) (2025)
- [Conceptualization, Operationalization, and Measurement of Machine Companionship: A Scoping Review](https://mlsanity.com/paper/2506.18119/) (2025)
- [Designing Beyond Language: Sociotechnical Barriers in AI Health Technologies for Limited English Proficiency](https://mlsanity.com/paper/2511.07277/) (2025)
- [Bridging Cultural Distance Between Models Default and Local Classroom Demands: How Global Teachers Adopt GenAI to Support Everyday Teaching Practices](https://mlsanity.com/paper/2509.10780/) (2025)
- [Exploring Human Perceptions of AI Responses: Insights from a Mixed-Methods Study on Risk Mitigation in Generative Models](https://mlsanity.com/paper/2512.01892/) (2025)
- [Adaptive Prompt Elicitation for Text-to-Image Generation](https://mlsanity.com/paper/2602.04713/) (2026)
- [Power Echoes: Investigating Moderation Biases in Online Power-Asymmetric Conflicts](https://mlsanity.com/paper/2603.01457/) (2026)
- ["I followed what felt right, not what I was told": Autonomy, Coaching, and Recognizing Bias Through AI-Mediated Dialogue](https://mlsanity.com/paper/2603.11274/) (2026)
- [Disrupted Companionship: A Risk Assessment Framework and Cross-Platform Quantitative Analysis of Psychosocial Responses to AI Companion Disruptions](https://mlsanity.com/paper/2609.16907/) (2026)

## Abstract (arXiv)

Large language model-based AI companions are increasingly viewed by users as friends or romantic partners, leading to deep emotional bonds. However, they can generate biased, discriminatory, and harmful outputs. Recently, users are taking the initiative to address these harms and re-align AI companions. We introduce the concept of user-driven value alignment, where users actively identify, challenge, and attempt to correct AI outputs they perceive as harmful, aiming to guide the AI to better align with their values. We analyzed 77 social media posts about discriminatory AI statements and conducted semi-structured interviews with 20 experienced users. Our analysis revealed six common types of discriminatory statements perceived by users, how users make sense of those AI behaviors, and seven user-driven alignment strategies, such as gentle persuasion and anger expression. We discuss implications for supporting user-driven value alignment in future AI systems, where users and their communities have greater agency.