# Dehumanizing Machines: Mitigating Anthropomorphic Behaviors in Text Generation Systems

arXiv: https://arxiv.org/abs/2502.14019 · HTML: https://mlsanity.com/paper/2502.14019/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 72 references that are in the map.
- First posted on arXiv 19 Feb 2025.

## Builds on (most cited first, 23 of 23)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Improving alignment of dialogue agents via targeted human judgements](https://mlsanity.com/paper/2209.14375/) (2022)
- [LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation Dataset](https://mlsanity.com/paper/2309.11998/) (2023)
- [UltraFeedback: Boosting Language Models with Scaled AI Feedback](https://mlsanity.com/paper/2310.01377/) (2023)
- [HateCheck: Functional Tests for Hate Speech Detection Models](https://mlsanity.com/paper/2012.15606/) (2020)
- [Talking About Large Language Models](https://mlsanity.com/paper/2212.03551/) (2022)
- [Harms from Increasingly Agentic Algorithmic Systems](https://mlsanity.com/paper/2302.10329/) (2023)
- [DICES Dataset: Diversity in Conversational AI Evaluation for Safety](https://mlsanity.com/paper/2306.11247/) (2023)
- [Could a Large Language Model be Conscious?](https://mlsanity.com/paper/2303.07103/) (2023)
- [AnthroScore: A Computational Linguistic Measure of Anthropomorphism](https://mlsanity.com/paper/2402.02056/) (2024)
- [From Lived Experience to Insight: Unpacking the Psychological Risks of Using AI Conversational Agents](https://mlsanity.com/paper/2412.07951/) (2024)
- [Language Models in Dialogue: Conversational Maxims for Human-AI Interactions](https://mlsanity.com/paper/2403.15115/) (2024)
- [Beyond Behaviorist Representational Harms: A Plan for Measurement and Mitigation](https://mlsanity.com/paper/2402.01705/) (2024)
- [The R-U-A-Robot Dataset: Helping Avoid Chatbot Deception by Detecting User Questions About Human or Non-Human Identity](https://mlsanity.com/paper/2106.02692/) (2021)
- ["One-Size-Fits-All"? Examining Expectations around What Constitute "Fair" or "Good" NLG System Behaviors](https://mlsanity.com/paper/2310.15398/) (2023)
- [Characterizing and modeling harms from interactions with design patterns in AI interfaces](https://mlsanity.com/paper/2404.11370/) (2024)
- [Robots-Dont-Cry: Understanding Falsely Anthropomorphic Utterances in Dialog Systems](https://mlsanity.com/paper/2210.12429/) (2022)
- ["I Am the One and Only, Your Cyber BFF": Understanding the Impact of GenAI Requires Understanding the Impact of Anthropomorphic AI](https://mlsanity.com/paper/2410.08526/) (2024)
- [Human-AI Interactions Through A Gricean Lens](https://mlsanity.com/paper/2106.09140/) (2021)
- [Affective Conversational Agents: Understanding Expectations and Personal Influences](https://mlsanity.com/paper/2310.12459/) (2023)
- [Understanding Communication Preferences of Information Workers in Engagement with Text-Based Conversational Agents](https://mlsanity.com/paper/2410.20468/) (2024)
- [Reputation Management in the ChatGPT Era](https://mlsanity.com/paper/2412.06356/) (2024)

## Built on by (most cited first, 11 of 11)

- [ELEPHANT: Measuring and understanding social sycophancy in LLMs](https://mlsanity.com/paper/2505.13995/) (2025)
- [WINA: Weight Informed Neuron Activation for Accelerating Large Language Model Inference](https://mlsanity.com/paper/2505.19427/) (2025)
- [Unraveling Interwoven Roles of Large Language Models in Authorship Privacy: Obfuscation, Mimicking, and Verification](https://mlsanity.com/paper/2505.14195/) (2025)
- [Artificial Impressions: Evaluating Large Language Model Behavior Through the Lens of Trait Impressions](https://mlsanity.com/paper/2510.08915/) (2025)
- [Seeking Late Night Life Lines: Experiences of Conversational AI Use in Mental Health Crisis](https://mlsanity.com/paper/2512.23859/) (2025)
- [Cultural Compass: A Framework for Organizing Societal Norms to Detect Violations in Human-AI Conversations](https://mlsanity.com/paper/2601.07973/) (2026)
- [Strategic Polysemy in AI Discourse: A Philosophical Analysis of Language, Hype, and Power](https://mlsanity.com/paper/2604.21043/) (2026)
- [Breaking the Illusion of Identity in LLM Tooling](https://mlsanity.com/paper/2604.07398/) (2026)
- [Examining Human-Like Behaviors in LLMs: A Multi-Dimensional Analysis of Model Behaviors, User Factors, and System Prompts](https://mlsanity.com/paper/2606.18258/) (2026)
- [Psychological Influences of Conversational AI: Research and Design Directions for Reducing Harm and Promoting Well-Being](https://mlsanity.com/paper/2607.25057/) (2026)
- [Long-term Measurements: Towards a Longitudinal Understanding of Human-AI Interactions](https://mlsanity.com/paper/2608.02491/) (2026)

## Abstract (arXiv)

As text generation systems' outputs are increasingly anthropomorphic -- perceived as human-like -- scholars have also increasingly raised concerns about how such outputs can lead to harmful outcomes, such as users over-relying or developing emotional dependence on these systems. How to intervene on such system outputs to mitigate anthropomorphic behaviors and their attendant harmful outcomes, however, remains understudied. With this work, we aim to provide empirical and theoretical grounding for developing such interventions. To do so, we compile an inventory of interventions grounded both in prior literature and a crowdsourcing study where participants edited system outputs to make them less human-like. Drawing on this inventory, we also develop a conceptual framework to help characterize the landscape of possible interventions, articulate distinctions between different types of interventions, and provide a theoretical basis for evaluating the effectiveness of different interventions.