# Personalities at Play: Probing Alignment in AI Teammates

arXiv: https://arxiv.org/abs/2603.00429 · HTML: https://mlsanity.com/paper/2603.00429/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 64 references that are in the map.
- First posted on arXiv 28 Feb 2026.

## Builds on (most cited first, 20 of 20)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studies](https://mlsanity.com/paper/2208.10264/) (2022)
- [LLM Agents Grounded in Self-Reports Enable General-Purpose Simulation of Individuals](https://mlsanity.com/paper/2411.10109/) (2024)
- [PersonaLLM: Investigating the Ability of Large Language Models to Express Personality Traits](https://mlsanity.com/paper/2305.02547/) (2023)
- [Two Tales of Persona in LLMs: A Survey of Role-Playing and Personalization](https://mlsanity.com/paper/2406.01171/) (2024)
- [Quantifying the Persona Effect in LLM Simulations](https://mlsanity.com/paper/2402.10811/) (2024)
- [Why human-AI relationships need socioaffective alignment](https://mlsanity.com/paper/2502.02528/) (2025)
- [Personality Alignment of Large Language Models](https://mlsanity.com/paper/2408.11779/) (2024)
- [Building Better AI Agents: A Provocation on the Utilisation of Persona in LLM-based Conversational Agents](https://mlsanity.com/paper/2407.11977/) (2024)
- [Can LLM Agents Maintain a Persona in Discourse?](https://mlsanity.com/paper/2502.11843/) (2025)
- [Understanding the Role of User Profile in the Personalization of Large Language Models](https://mlsanity.com/paper/2406.17803/) (2024)
- [Group Communication Analysis: A Computational Linguistics Approach for Detecting Sociocognitive Roles in Multi-Party Interactions](https://mlsanity.com/paper/1801.03563/) (2018)
- [PersonaTeaming: Exploring How Introducing Personas Can Improve Automated AI Red-Teaming](https://mlsanity.com/paper/2509.03728/) (2025)
- [The influence of persona and conversational task on social interactions with a LLM-controlled embodied conversational agent](https://mlsanity.com/paper/2411.05653/) (2024)
- [Catalyzing Equity in STEM Teams: Harnessing Generative AI for Inclusion and Diversity](https://mlsanity.com/paper/2402.00037/) (2024)
- [Design principles for a hybrid intelligence decision support system for business model validation](https://mlsanity.com/paper/2105.03356/) (2021)
- [The AI Collaborator: Bridging Human-AI Interaction in Educational and Professional Settings](https://mlsanity.com/paper/2405.10460/) (2024)
- [Deterministic AI Agent Personality Expression through Standard Psychological Diagnostics](https://mlsanity.com/paper/2503.17085/) (2025)
- [AI-exhibited Personality Traits Can Shape Human Self-concept through Conversations](https://mlsanity.com/paper/2601.12727/) (2026)
- [Read the Room or Lead the Room: Understanding Socio-Cognitive Dynamics in Human-AI Teaming](https://mlsanity.com/paper/2510.09944/) (2025)

## Built on by (most cited first, 1 of 1)

- [TRAIL: A Platform for Configurable Human--AI Teaming Experiments](https://mlsanity.com/paper/2607.12180/) (2026)

## Abstract (arXiv)

Collaborative problem solving and learning are shaped by who or what is on the team. As large language models (LLMs) increasingly function as collaborators rather than tools, a key question is whether AI teammates can be aligned to express personality in predictable ways that matter for interaction and learning. We investigate AI personality alignment through a three-lens evaluation framework spanning self-perception (standardized self-report), behavioral expression (team dialogue), and reflective expression (memory construction). We first administered the Big Five Inventory (BFI-44) to LLM-based teammates across four providers (GPT-4o, Claude-3.7 Sonnet, Gemini-2.5 Pro, Grok-3), 32 high/low trait configurations, and multiple prompting strategies. LLMs produced sharply differentiated Big Five profiles, but prompt semantic richness added little beyond simple trait assignment, while provider differences and baseline "default" personalities were substantial. Role framing also mattered: several models refused the assessment without context, yet complied when framed as a collaborative teammate. We then simulated AI participation in authentic team transcripts using high-trait personas and analyzed both generated utterances and structured long-term memories with LIWC-22. Personality signals in conversation were generally subtle and most detectable for Extraversion, whereas memory representations amplified trait-specific signals, especially for Neuroticism, Conscientiousness, and Agreeableness; Openness remained difficult to elicit robustly. Together, results suggest that AI personality is measurable but multi-layered and context-dependent, and that evaluating personality-aligned AI teammates requires attention to memory and system-level design, not conversation-only behavior.