# Interpretable Humans, Alien LLMs: Expert Analysis of Latent Structures in Assessment Responses

arXiv: https://arxiv.org/abs/2608.17810 · HTML: https://mlsanity.com/paper/2608.17810/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 57 references that are in the map.
- First posted on arXiv 18 Aug 2026.

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

- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [AGIEval: A Human-Centric Benchmark for Evaluating Foundation Models](https://mlsanity.com/paper/2304.06364/) (2023)
- [NLP Evaluation in trouble: On the Need to Measure LLM Data Contamination for each Benchmark](https://mlsanity.com/paper/2310.18018/) (2023)
- [MathArena: Evaluating LLMs on Uncontaminated Math Competitions](https://mlsanity.com/paper/2505.23281/) (2025)
- [Large Language Models Fail on Trivial Alterations to Theory-of-Mind Tasks](https://mlsanity.com/paper/2302.08399/) (2023)
- [What can Large Language Models do in chemistry? A comprehensive benchmark on eight tasks](https://mlsanity.com/paper/2305.18365/) (2023)
- [ProSA: Assessing and Understanding the Prompt Sensitivity of LLMs](https://mlsanity.com/paper/2410.12405/) (2024)
- [A Systematic Survey and Critical Review on Evaluating Large Language Models: Challenges, Limitations, and Recommendations](https://mlsanity.com/paper/2407.04069/) (2024)
- [Position: Evaluating Generative AI Systems Is a Social Science Measurement Challenge](https://mlsanity.com/paper/2502.00561/) (2025)
- [Measurement to Meaning: A Validity-Centered Framework for AI Evaluation](https://mlsanity.com/paper/2505.10573/) (2025)
- [Which of These Best Describes Multiple Choice Evaluation with LLMs? A) Forced B) Flawed C) Fixable D) All of the Above](https://mlsanity.com/paper/2502.14127/) (2025)
- [Probing the limitations of multimodal language models for chemistry and materials research](https://mlsanity.com/paper/2411.16955/) (2024)
- [Limited Ability of LLMs to Simulate Human Psychological Behaviours: a Psychometric Analysis](https://mlsanity.com/paper/2405.07248/) (2024)
- [Leveraging LLM-Respondents for Item Evaluation: a Psychometric Analysis](https://mlsanity.com/paper/2407.10899/) (2024)
- [ECBD: Evidence-Centered Benchmark Design for NLP](https://mlsanity.com/paper/2406.08723/) (2024)
- [GreekBarBench: A Challenging Benchmark for Free-Text Legal Reasoning and Citations](https://mlsanity.com/paper/2505.17267/) (2025)
- [Do LLMs Give Psychometrically Plausible Responses in Educational Assessments?](https://mlsanity.com/paper/2506.09796/) (2025)
- [Forget What You Know about LLMs Evaluations -- LLMs are Like a Chameleon](https://mlsanity.com/paper/2502.07445/) (2025)
- [Examining the Potential and Pitfalls of ChatGPT in Science and Engineering Problem-Solving](https://mlsanity.com/paper/2310.08773/) (2023)
- [Could ChatGPT get an Engineering Degree? Evaluating Higher Education Vulnerability to AI Assistants](https://mlsanity.com/paper/2408.11841/) (2024)
- [DCR: Quantifying Data Contamination in LLMs Evaluation](https://mlsanity.com/paper/2507.11405/) (2025)
- [Bilingual Evaluation of Language Models on General Knowledge in University Entrance Exams with Minimal Contamination](https://mlsanity.com/paper/2409.12746/) (2024)
- [Applying IRT to Distinguish Between Human and Generative AI Responses to Multiple-Choice Assessments](https://mlsanity.com/paper/2412.02713/) (2024)
- [Do Assessment Instruments Measure the Same Thing for Humans and LLMs? A Latent Structure Analysis](https://mlsanity.com/paper/2608.15630/) (2026)

## Abstract (arXiv)

The evaluation of large language models (LLMs) relies heavily on human-designed assessments, implicitly assuming that AI and humans employ similar underlying cognitive constructs. Challenging this assumption, we investigate whether the latent factors governing LLM performance carry the same substantive, human-interpretable meaning as the cognitive constructs governing human learners. Using responses from humans and six LLMs across quantitative reasoning and chemistry assessments, we conducted Exploratory Factor Analysis (EFA) separately for both groups. Subject-Matter Experts (SMEs) then blindly evaluated the resulting factor graphs to ascribe pedagogical meaning to the emerged constructs. SMEs successfully interpreted most of the human-derived factors. Conversely, they could not ascribe meaning to any LLM-derived factors in quantitative reasoning and interpreted only half of the LLM factors in chemistry. By combining data-driven EFA with blind expert interpretation, this framework shows that LLMs frequently operate on statistically opaque mechanisms distinct from human reasoning.