# TUX: Measuring Human--AI Tacit Understanding

arXiv: https://arxiv.org/abs/2605.30930 · HTML: https://mlsanity.com/paper/2605.30930/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 56 references that are in the map.
- First posted on arXiv 29 May 2026.

## Builds on (most cited first, 24 of 24)

- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Steering Language Models With Activation Engineering](https://mlsanity.com/paper/2308.10248/) (2023)
- [LLM Agents Grounded in Self-Reports Enable General-Purpose Simulation of Individuals](https://mlsanity.com/paper/2411.10109/) (2024)
- [From Persona to Personalization: A Survey on Role-Playing Language Agents](https://mlsanity.com/paper/2404.18231/) (2024)
- [Two Tales of Persona in LLMs: A Survey of Role-Playing and Personalization](https://mlsanity.com/paper/2406.01171/) (2024)
- [Spectral Editing of Activations for Large Language Model Alignment](https://mlsanity.com/paper/2405.09719/) (2024)
- [Personalized Large Language Models](https://mlsanity.com/paper/2402.09269/) (2024)
- [Prototypical Human-AI Collaboration Behaviors from LLM-Assisted Writing in the Wild](https://mlsanity.com/paper/2505.16023/) (2025)
- [SPIN-Bench: How Well Do LLMs Plan Strategically and Reason Socially?](https://mlsanity.com/paper/2503.12349/) (2025)
- [Can LLM "Self-report"?: Evaluating the Validity of Self-report Scales in Measuring Personality Design in LLM-based Chatbots](https://mlsanity.com/paper/2412.00207/) (2024)
- [Constrained Human-AI Cooperation: An Inclusive Embodied Social Intelligence Challenge](https://mlsanity.com/paper/2411.01796/) (2024)
- [Evaluating Generalization Capabilities of LLM-Based Agents in Mixed-Motive Scenarios Using Concordia](https://mlsanity.com/paper/2512.03318/) (2025)
- [AI on My Shoulder: Supporting Emotional Labor in Front-Office Roles with an LLM-based Empathetic Coworker](https://mlsanity.com/paper/2411.02408/) (2024)
- [Demystifying Tacit Knowledge in Graphic Design: Characteristics, Instances, Approaches, and Guidelines](https://mlsanity.com/paper/2403.06252/) (2024)
- [Your Co-Workers Matter: Evaluating Collaborative Capabilities of Language Models in Blocks World](https://mlsanity.com/paper/2404.00246/) (2024)
- [PAIR-SAFE: A Paired-Agent Approach for Runtime Auditing and Refining AI-Mediated Mental Health Support](https://mlsanity.com/paper/2601.12754/) (2026)
- [Do Role-Playing Agents Practice What They Preach? Belief-Behavior Consistency in LLM-Based Simulations of Human Trust](https://mlsanity.com/paper/2507.02197/) (2025)
- [Do We Know What They Know We Know? Calibrating Student Trust in AI and Human Responses Through Mutual Theory of Mind](https://mlsanity.com/paper/2601.16960/) (2026)
- [AI Psychosis: Does Conversational AI Amplify Delusion-Related Language?](https://mlsanity.com/paper/2603.19574/) (2026)
- [VASTU: Language Models Struggle to Recognize Online Community Values](https://mlsanity.com/paper/2601.12491/) (2026)
- [Not My Truce: Personality Differences in AI-Mediated Workplace Negotiation](https://mlsanity.com/paper/2604.00464/) (2026)
- [LLUMI: Improving LLM Writing Assistance for Mental Health Support with Online Community Feedback](https://mlsanity.com/paper/2605.30273/) (2026)
- [CHOIR: A Chatbot-mediated Organizational Memory Leveraging Communication in University Research Labs](https://mlsanity.com/paper/2509.20512/) (2025)

## Abstract (arXiv)

As large language models (LLMs) increasingly act as collaborative partners, human--AI alignment is often evaluated through explicit task success, accuracy, or reward optimization. Yet many collaborative settings depend on tacit understanding: whether an agent can align with a human's evaluative stance or representational priors without clear objectives, communication, or feedback. To study this capacity, we develop a spectrum-placement task inspired by the social party game Wavelength, in which humans and agents independently place concepts along subjective spectra. We operationalize the Tacit Understanding Index (TUX) as a pairwise behavioral measure of similarity between human and agent judgments, and evaluate it with 241 human participants and 200 profile-conditioned LLM agents across four models. We find that nearest human--agent pairs in trait space achieve significantly higher TUX, suggesting that tacit alignment is associated with person-level characteristics rather than reflecting only random similarity. Regression analyses show that TUX becomes more explainable as predictor sets become richer, with individual traits, decision-making styles, and confidence improving over aggregate trait-distance baselines. These findings suggest that TUX provides a measurable behavioral signal of human--LLM tacit understanding, while revealing the limits of profile-based conditioning for capturing deeper representational alignment.