# Every Token Counts: Exact Likert-Scale Distributions for Measuring LLM Attitudes and Biases

arXiv: https://arxiv.org/abs/2608.10503 · HTML: https://mlsanity.com/paper/2608.10503/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 45 references that are in the map.
- First posted on arXiv 11 Aug 2026.

## Builds on (most cited first, 18 of 18)

- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [A Survey on Large Language Model based Autonomous Agents](https://mlsanity.com/paper/2308.11432/) (2023)
- [Language Models (Mostly) Know What They Know](https://mlsanity.com/paper/2207.05221/) (2022)
- [The Rise and Potential of Large Language Model Based Agents: A Survey](https://mlsanity.com/paper/2309.07864/) (2023)
- [Whose Opinions Do Language Models Reflect?](https://mlsanity.com/paper/2303.17548/) (2023)
- [Towards Measuring the Representation of Subjective Global Opinions in Language Models](https://mlsanity.com/paper/2306.16388/) (2023)
- [PersonaLLM: Investigating the Ability of Large Language Models to Express Personality Traits](https://mlsanity.com/paper/2305.02547/) (2023)
- [WorldValuesBench: A Large-Scale Benchmark Dataset for Multi-Cultural Value Awareness of Language Models](https://mlsanity.com/paper/2404.16308/) (2024)
- [You don't need a personality test to know these models are unreliable: Assessing the Reliability of Large Language Models on Psychometric Instruments](https://mlsanity.com/paper/2311.09718/) (2023)
- [Break the Checkbox: Challenging Closed-Style Evaluations of Cultural Alignment in LLMs](https://mlsanity.com/paper/2502.08045/) (2025)
- [On The Origin of Cultural Biases in Language Models: From Pre-training Data to Linguistic Phenomena](https://mlsanity.com/paper/2501.04662/) (2025)
- [GD-COMET: A Geo-Diverse Commonsense Inference Model](https://mlsanity.com/paper/2310.15383/) (2023)
- [Value Drifts: Tracing Value Alignment During LLM Post-Training](https://mlsanity.com/paper/2510.26707/) (2025)
- [Do Psychometric Tests Work for Large Language Models? Evaluation of Tests on Sexism, Racism, and Morality](https://mlsanity.com/paper/2510.11254/) (2025)
- [Do You Know About My Nation? Investigating Multilingual Language Models' Cultural Literacy Through Factual Knowledge](https://mlsanity.com/paper/2511.00657/) (2025)
- [Is It Bad to Work All the Time? Cross-Cultural Evaluation of Social Norm Biases in GPT-4](https://mlsanity.com/paper/2505.18322/) (2025)
- [Tailored Emotional LLM-Supporter: Enhancing Cultural Sensitivity](https://mlsanity.com/paper/2508.07902/) (2025)
- [Artificial Impressions: Evaluating Large Language Model Behavior Through the Lens of Trait Impressions](https://mlsanity.com/paper/2510.08915/) (2025)

## Built on by (most cited first, 3 of 3)

- [Does Rank Still Matter? Position Bias When AI Agents Shop on Our Behalf](https://mlsanity.com/paper/2608.22697/) (2026)
- [Whom Do AI Agents Work For? Role Assignment Induces Sponsorship Bias in LLM Recommenders](https://mlsanity.com/paper/2609.17989/) (2026)
- [Shopping by algorithm: How agentic AI deploys human heuristics as a surrogate consumer](https://mlsanity.com/paper/2609.28372/) (2026)

## Abstract (arXiv)

As Large Language Models (LLMs) are increasingly deployed as autonomous agents, accurately evaluating their latent values and biases is critical. The NLP community typically evaluates models using large, unstructured benchmarks. While effective for general capabilities, these datasets fundamentally conflate causal mechanisms: even when an aggregate bias is detected, unstructured evaluations cannot disentangle whether it stems from baseline traits, contextual confounders, or complex interactions. To address this, we introduce an analytically exact framework for the controlled behavioral evaluation of LLMs. We bridge human psychometrics with LLM mechanics by resolving gaps in design, measurement, and analysis. First, we replace unstructured prompting with fully crossed factorial experiments to systematically isolate causal main and interaction effects. Second, we eliminate Monte Carlo text sampling noise by operating directly on exact, token-level Probability Mass Functions (PMFs). Third, we derive a multivariate ordinal consensus metric and a distributional ANOVA to process these PMFs analytically. We validate our framework with a case study on consumer ethnocentrism across five LLMs, demonstrating how our approach isolates systemic country-of-origin biases that aggregate benchmarks otherwise obscure.