Cognitive Thermometers: Machine Learning and Logical Complexity
Quick Answer
The article proposes that machine learning can serve as a more agnostic measure of semantic complexity compared to traditional logical definability.
Quick Take
It highlights emerging evidence that machine learning and logic often align on complexity but diverge in explanations, suggesting that machine learning models can act as 'cognitive thermometers' bridging symbolic logic and connectionist AI.
Key Points
- Machine learning provides a more neutral approach to measuring semantic complexity.
- Logic and machine learning often yield converging results on relative complexity.
- In cases of divergence, machine learning offers better explanations than logical complexity.
- The concept of 'cognitive thermometers' unifies symbolic logic and connectionist AI.
Paper Resources
📖 Reader Mode
~2 min readAbstract:How does the human mind represent semantic categories? Why do natural languages favor certain meanings over others? Prior explanations have relied on logical definability and complexity, but these are highly sensitive to the choice of logical language, rendering some design choices unmotivated. In this article, we propose that machine learning provides a somewhat more agnostic approach to measuring semantic complexity. We review emerging evidence that logic and machine learning often yield converging results on relative complexity and its resulting effects in semantic typology. Where they diverge, learning appears to be a better explanation than logical complexity. We argue that treating machine learning models as ``cognitive thermometers'' enables a unified approach to complexity that bridges symbolic logic and connectionist AI.
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.10724 [cs.CL] |
| (or arXiv:2610.10724v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.10724 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Jakub Szymanik [view email]
[v1]
Wed, 7 Oct 2026 18:04:45 UTC (3,052 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CL
See more →The "10th Juror": Open-Set Standpoint Screening for Bureaucratic Bias Detection
MARS-Gov introduces a framework for detecting bureaucratic bias in Dutch government documents, achieving a new state-of-the-art F1 score of 0.880. This model outperforms existing zero-shot detectors by 20.2 points and reduces unnecessary interventions to just 2.5%. The framework's dynamic '10th juror' adapts to emerging biases, enhancing legal language processing.