# Rethinking Psychometric Evaluation of LLMs: When and Why Self-Reports Predict Behavior

arXiv: https://arxiv.org/abs/2606.12730 · HTML: https://mlsanity.com/paper/2606.12730/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 20 of its 72 references that are in the map.
- First posted on arXiv 10 Jun 2026.

## Placed in

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

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

- [Towards Understanding Sycophancy in Language Models](https://mlsanity.com/paper/2310.13548/) (2023)
- [Scaling Synthetic Data Creation with 1,000,000,000 Personas](https://mlsanity.com/paper/2406.20094/) (2024)
- [PersonaLLM: Investigating the Ability of Large Language Models to Express Personality Traits](https://mlsanity.com/paper/2305.02547/) (2023)
- [Personality Traits in Large Language Models](https://mlsanity.com/paper/2307.00184/) (2023)
- [ELEPHANT: Measuring and understanding social sycophancy in LLMs](https://mlsanity.com/paper/2505.13995/) (2025)
- [Large Language Model Agent in Financial Trading: A Survey](https://mlsanity.com/paper/2408.06361/) (2024)
- [Randomness, Not Representation: The Unreliability of Evaluating Cultural Alignment in LLMs](https://mlsanity.com/paper/2503.08688/) (2025)
- [Large Language Model Psychometrics: A Systematic Review of Evaluation, Validation, and Enhancement](https://mlsanity.com/paper/2505.08245/) (2025)
- [Self-Assessment Tests are Unreliable Measures of LLM Personality](https://mlsanity.com/paper/2309.08163/) (2023)
- [Challenging the Validity of Personality Tests for Large Language Models](https://mlsanity.com/paper/2311.05297/) (2023)
- [Adaptation of Agentic AI: A Survey of Post-Training, Memory, and Skills](https://mlsanity.com/paper/2512.16301/) (2025)
- [Large Language Model Reasoning Failures](https://mlsanity.com/paper/2602.06176/) (2026)
- [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)
- [ChatGPT Based Data Augmentation for Improved Parameter-Efficient Debiasing of LLMs](https://mlsanity.com/paper/2402.11764/) (2024)
- [A Pragmatic View of AI Personhood](https://mlsanity.com/paper/2510.26396/) (2025)
- [Beyond Profile: From Surface-Level Facts to Deep Persona Simulation in LLMs](https://mlsanity.com/paper/2502.12988/) (2025)
- [Do Psychometric Tests Work for Large Language Models? Evaluation of Tests on Sexism, Racism, and Morality](https://mlsanity.com/paper/2510.11254/) (2025)
- [How and Why LLMs Generalize: A Fine-Grained Analysis of LLM Reasoning from Cognitive Behaviors to Low-Level Patterns](https://mlsanity.com/paper/2512.24063/) (2025)
- [Steer2Adapt: Dynamically Composing Steering Vectors Elicits Efficient Adaptation of LLMs](https://mlsanity.com/paper/2602.07276/) (2026)
- [Interactive Evaluation Requires a Design Science](https://mlsanity.com/paper/2605.17829/) (2026)

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

- [Exposure is not manifestation: measurement target and output resolution jointly determine which behavioural-faithfulness evaluator wins](https://mlsanity.com/paper/2607.09306/) (2026)

## Abstract (arXiv)

Anticipating LLM behavioral tendencies from low-cost psychometric probes is critical for safe deployment, but only if self-reports (SR) reliably predict behavior. Recent work documented substantial SR-behavior dissociation in LLMs, but relied on broad personality traits (Big 5) that predict specific behaviors weakly, even in humans. Furthermore, the isolation of conversational sessions combined with weak context matching left open whether LLMs truly lack coherence or whether the conditions needed to detect such coherence were not met. We contrast Big 5 with the Theory of Planned Behavior (TPB), which measures intention targeted to a specific behavior and predicts human behavior substantially better than broad traits. We run experiments across four behavioral tasks and 11 frontier LLMs, while also varying session context and identity induction. We find that SR-behavior coherence exists but is selective. 1) Within a shared conversation, the Theory of Planned Behavior reaches human-level coherence; Big 5 does not. 2) Across separate conversations, coherence survives only for behaviors anchored outside the immediate prompt, such as implicit bias shaped by training, and collapses when behavior is strongly primed by context, as with sycophancy. 3) Persona prompting makes self-reports more consistent across conversations, but does not bring behavior into alignment. These findings suggest that coarse personality frameworks, such as Big 5 may not be the best tools for testing deployment behavior. More task- and behavior-specific instruments are needed, and even these must be evaluated across tasks and contexts.