# Humanizing Machines: Rethinking LLM Anthropomorphism Through a Multi-Level Framework of Design

arXiv: https://arxiv.org/abs/2508.17573 · HTML: https://mlsanity.com/paper/2508.17573/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 32 of its 119 references that are in the map.
- First posted on arXiv 25 Aug 2025.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 30 of 32)

- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [From Persona to Personalization: A Survey on Role-Playing Language Agents](https://mlsanity.com/paper/2404.18231/) (2024)
- [Large Pre-trained Language Models Contain Human-like Biases of What is Right and Wrong to Do](https://mlsanity.com/paper/2103.11790/) (2021)
- [PutnamBench: Evaluating Neural Theorem-Provers on the Putnam Mathematical Competition](https://mlsanity.com/paper/2407.11214/) (2024)
- [Lawyer LLaMA Technical Report](https://mlsanity.com/paper/2305.15062/) (2023)
- [Emotionally Numb or Empathetic? Evaluating How LLMs Feel Using EmotionBench](https://mlsanity.com/paper/2308.03656/) (2023)
- [Understanding Aha Moments: from External Observations to Internal Mechanisms](https://mlsanity.com/paper/2504.02956/) (2025)
- [A Survey of Large Language Model Agents for Question Answering](https://mlsanity.com/paper/2503.19213/) (2025)
- [Trust No Bot: Discovering Personal Disclosures in Human-LLM Conversations in the Wild](https://mlsanity.com/paper/2407.11438/) (2024)
- [Embodied-RAG: General Non-parametric Embodied Memory for Retrieval and Generation](https://mlsanity.com/paper/2409.18313/) (2024)
- [Believing Anthropomorphism: Examining the Role of Anthropomorphic Cues on Trust in Large Language Models](https://mlsanity.com/paper/2405.06079/) (2024)
- [AI PERSONA: Towards Life-long Personalization of LLMs](https://mlsanity.com/paper/2412.13103/) (2024)
- [Speech Synthesis with Mixed Emotions](https://mlsanity.com/paper/2208.05890/) (2022)
- [Who is ChatGPT? Benchmarking LLMs' Psychological Portrayal Using PsychoBench](https://mlsanity.com/paper/2310.01386/) (2023)
- [Social Genome: Grounded Social Reasoning Abilities of Multimodal Models](https://mlsanity.com/paper/2502.15109/) (2025)
- [Multi-turn Evaluation of Anthropomorphic Behaviours in Large Language Models](https://mlsanity.com/paper/2502.07077/) (2025)
- [Synthetic Socratic Debates: Examining Persona Effects on Moral Decision and Persuasion Dynamics](https://mlsanity.com/paper/2506.12657/) (2025)
- [Designing for Human-Agent Alignment: Understanding what humans want from their agents](https://mlsanity.com/paper/2404.04289/) (2024)
- [Rel-A.I.: An Interaction-Centered Approach To Measuring Human-LM Reliance](https://mlsanity.com/paper/2407.07950/) (2024)
- [The Illusion of Empathy: How AI Chatbots Shape Conversation Perception](https://mlsanity.com/paper/2411.12877/) (2024)
- [HumT DumT: Measuring and controlling human-like language in LLMs](https://mlsanity.com/paper/2502.13259/) (2025)
- [AI Automatons: AI Systems Intended to Imitate Humans](https://mlsanity.com/paper/2503.02250/) (2025)
- [Embracing Contradiction: Theoretical Inconsistency Will Not Impede the Road of Building Responsible AI Systems](https://mlsanity.com/paper/2505.18139/) (2025)
- ["I Like Sunnie More Than I Expected!": Exploring User Expectation and Perception of an Anthropomorphic LLM-based Conversational Agent for Well-Being Support](https://mlsanity.com/paper/2405.13803/) (2024)
- [Guess What I am Thinking: A Benchmark for Inner Thought Reasoning of Role-Playing Language Agents](https://mlsanity.com/paper/2503.08193/) (2025)
- [When LLMs Learn to be Students: The SOEI Framework for Modeling and Evaluating Virtual Student Agents in Educational Interaction](https://mlsanity.com/paper/2410.15701/) (2024)
- [RoboReflect: A Robotic Reflective Reasoning Framework for Grasping Ambiguous-Condition Objects](https://mlsanity.com/paper/2501.09307/) (2025)
- [Giving AI Personalities Leads to More Human-Like Reasoning](https://mlsanity.com/paper/2502.14155/) (2025)
- [Affective and Conversational Predictors of Re-Engagement in Human-Robot Interactions -- A Student-Centered Study with A Humanoid Social Robot](https://mlsanity.com/paper/2503.16449/) (2025)
- [Speaking of Trust -- Speech as a Measure of Trust](https://mlsanity.com/paper/2104.05340/) (2021)

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

- [The Personality Illusion: Revealing Dissociation Between Self-Reports & Behavior in LLMs](https://mlsanity.com/paper/2509.03730/) (2025)
- [Hire Your Anthropologist! Rethinking Culture Benchmarks Through an Anthropological Lens](https://mlsanity.com/paper/2510.05931/) (2025)
- [The Chameleon's Limit: Investigating Persona Collapse and Homogenization in Large Language Models](https://mlsanity.com/paper/2604.24698/) (2026)
- [Towards Valid Student Simulation with Large Language Models](https://mlsanity.com/paper/2601.05473/) (2026)
- [Do Persona-Infused LLMs Affect Performance in a Strategic Reasoning Game?](https://mlsanity.com/paper/2512.06867/) (2025)
- [Love First, Know Later: Persona-Based Romantic Compatibility Through LLM Text World Engines](https://mlsanity.com/paper/2512.11844/) (2025)
- [Sentipolis: Emotion-Aware Agents for Social Simulations](https://mlsanity.com/paper/2601.18027/) (2026)
- [The Psychology of Learning from Machines: Anthropomorphic AI and the Paradox of Automation in Education](https://mlsanity.com/paper/2601.06172/) (2026)
- [Implicit Humanization in Everyday LLM Moral Judgments](https://mlsanity.com/paper/2604.22764/) (2026)
- [Not What, But How: A Framework for Auditing LLM Responses across Positioning, Generalization, Anthropomorphism, and Maxims](https://mlsanity.com/paper/2606.02493/) (2026)
- [The Epistemic Politics of AI Anthropomorphism](https://mlsanity.com/paper/2608.00961/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) increasingly exhibit anthropomorphism characteristics -- human-like qualities portrayed across their outlook, language, behavior, and reasoning functions. Such characteristics enable more intuitive and engaging human-AI interactions. However, current research on anthropomorphism remains predominantly risk-focused, emphasizing over-trust and user deception while offering limited design guidance. We argue that anthropomorphism should instead be treated as a concept of design that can be intentionally tuned to support user goals. Drawing from multiple disciplines, we propose that the anthropomorphism of an LLM-based artifact should reflect the interaction between artifact designers and interpreters. This interaction is facilitated by cues embedded in the artifact by the designers and the (cognitive) responses of the interpreters to the cues. Cues are categorized into four dimensions: textitperceptive, linguistic, behavioral, and textitcognitive. By analyzing the manifestation and effectiveness of each cue, we provide a unified taxonomy with actionable levers for practitioners. Consequently, we advocate for function-oriented evaluations of anthropomorphic design.